{ "metadata": { "schema_version": "1.0.0", "profile_id": "02-01", "created_at": "2026-09-22", "as_of_date": "2026-09-22", "record_kind": "fictional_sample", "verification_status": "not_verified", "is_real_person_record": false, "disclaimer": "Fictional demonstration candidate. All employers, education, projects, achievements and outcomes are illustrative and unverified. Not a real application or licence record.", "source_basis": { "biography": "original synthetic example", "structure_reference": "sr-software-engineer-fullstack-angular-react-nodejs.pdf", "reference_used_for": "section hierarchy and visual direction only; no Ajay Prajapat biographical claims copied", "web_reference": "https://kyros.on3-step.com/homereveal", "web_reference_status": "requested inspiration; live JavaScript visual layout could not be independently rendered" }, "category": { "id": 2, "name": "AI, Data & Analytics", "role_index": 1, "role_title": "AI Engineer" }, "publishing": { "search_indexing": false, "external_contact_enabled": false, "real_credentials_required_before_publication": true } }, "basics": { "name": "Vihaan Mehta", "headline": "AI Engineer", "specialisation": "Python, retrieval systems, LLM evaluation", "location": { "city": "Pune", "country": "India" }, "contact": { "email": "vihaan.mehta@example.com", "phone": null, "website": null, "linkedin": null, "portfolio_url": null, "contact_status": "placeholder_not_for_contact" }, "career_start_date": "2013-07-01", "experience_years": 13, "seniority": "experienced specialist", "languages": [ { "language": "English", "proficiency": "professional working - fictional sample" }, { "language": "Hindi", "proficiency": "professional working - fictional sample" } ], "work_preferences": { "arrangement": "hybrid; remote feasibility discussed per role", "relocation": "open to discussion - sample preference", "availability": "not confirmed; discuss before an interview", "employment_interest": [ "full-time", "defined project or fixed-term work where appropriate" ] } }, "executive_summary": [ "AI Engineer with an illustrative 13-year career in analytics, decision support and applied machine learning. Combines python, retrieval systems, llm evaluation with disciplined documentation, practical coordination and clear communication. The sample career progresses from focused execution to independent workstream ownership, with responsibilities and boundaries described for each appointment.", "Selected work includes grounded knowledge assistant, document intake assistant and ai evaluation workbench. These examples explain the original problem, individual contribution, deliverables, review approach and remaining limitations rather than relying on unsupported headline claims.", "Prepared for experienced ai engineer opportunities requiring dependable delivery, thoughtful professional judgement and collaboration. The qualification narrative includes M.Tech in Artificial Intelligence. Every named organisation and outcome in this record is fictional; professional eligibility is not independently established." ], "professional_mission": "Turn a clear brief into dependable analytics, decision support and applied machine learning work: understand the context, apply python and retrieval systems, record the evidence and explain the limitations before handover.", "core_competencies": [ { "name": "Python", "level": "advanced practice - illustrative", "application": "Applied to grounded knowledge assistant through documented preparation, execution and review.", "evidence_project_id": "P1" }, { "name": "retrieval systems", "level": "advanced practice - illustrative", "application": "Applied to document intake assistant through documented preparation, execution and review.", "evidence_project_id": "P2" }, { "name": "LLM evaluation", "level": "advanced practice - illustrative", "application": "Applied to ai evaluation workbench through documented preparation, execution and review.", "evidence_project_id": "P3" }, { "name": "FastAPI", "level": "advanced practice - illustrative", "application": "Applied to grounded knowledge assistant through documented preparation, execution and review.", "evidence_project_id": "P1" }, { "name": "vector search", "level": "advanced practice - illustrative", "application": "Applied to document intake assistant through documented preparation, execution and review.", "evidence_project_id": "P2" }, { "name": "tool orchestration", "level": "advanced practice - illustrative", "application": "Applied to ai evaluation workbench through documented preparation, execution and review.", "evidence_project_id": "P3" }, { "name": "prompt testing", "level": "advanced practice - illustrative", "application": "Applied to grounded knowledge assistant through documented preparation, execution and review.", "evidence_project_id": "P1" }, { "name": "data access controls", "level": "advanced practice - illustrative", "application": "Applied to document intake assistant through documented preparation, execution and review.", "evidence_project_id": "P2" } ], "specialist_practice": { "title": "Evaluation and data stewardship", "summary": "Examples use synthetic or permissioned data; no claim is made that a model is safe for an untested population.", "working_principles": [ "Define the decision, data lineage and evaluation boundary before choosing a method.", "Separate development, validation and holdout data and record known failure modes.", "Document uncertainty, monitoring ownership and human review for consequential uses." ], "tools_and_methods": [ "Python", "retrieval systems", "LLM evaluation", "FastAPI", "vector search", "tool orchestration", "prompt testing", "data access controls" ], "professional_scope": "The sample focuses on python, retrieval systems, llm evaluation. Approvals, supervision and specialist input are identified in each work package; work outside this scope is referred to the designated responsible person." }, "projects": [ { "id": "P1", "title": "Grounded knowledge assistant", "category": "Python", "organisation": "Meridian Analytics Research (fictional)", "employment_id": "EXP-4", "start_date": "2023-01-01", "end_date": "2023-06-30", "project_context": "Fictional internal work programme in analytics, decision support and applied machine learning; not a real client case study.", "problem": "Internal answers lacked traceable evidence.", "objective": "Create a workable response to this issue through python, explicit review criteria and practical documentation. Agree the boundaries before execution and retain unresolved points for follow-up.", "role_and_ownership": "AI Engineer; owned the stated workstream, not the full organisation or every collaborator contribution.", "contribution": [ "Built retrieval with passage citations and abstention checks.", "Prepared the scope with the commissioning team, identified unresolved inputs and used python to turn the brief into a sequenced work package.", "Applied retrieval systems and llm evaluation while coordinating reviews with the designated owner. Kept decision notes so collaborators could separate facts, assumptions and changes.", "Assembled the handover material, explained open limitations and agreed which items needed further review rather than presenting them as completed." ], "methods": [ "Python", "retrieval systems", "LLM evaluation", "FastAPI" ], "deliverables": [ "Grounded knowledge assistant - scoped brief", "Grounded knowledge assistant - reviewed working package", "Grounded knowledge assistant - handover and learning summary" ], "review_method": "Reviewed the scoped output against the agreed brief, recorded exceptions and checked that key conclusions could be traced to observations. The review package calls for a data-quality and lineage note and a named human reviewer.", "outcomes": [ "Illustrative outcome: the team adopted a repeatable approach for grounded knowledge assistant, with clearer ownership and reviewable records. This is a fictional qualitative result; no real performance measurement or external acceptance evidence is supplied." ], "metrics": [], "limitations": "Synthetic demonstration only. Examples use synthetic or permissioned data; no claim is made that a model is safe for an untested population. No underlying client documents, independently verified measurements or signed approval records are attached.", "evidence": [ { "id": "E1.1", "title": "Grounded knowledge assistant: data-quality and lineage note", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" }, { "id": "E1.2", "title": "Grounded knowledge assistant: evaluation protocol", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" }, { "id": "E1.3", "title": "Grounded knowledge assistant: model or analysis review", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" } ], "verification_status": "not_verified" }, { "id": "P2", "title": "Document intake assistant", "category": "retrieval systems", "organisation": "Meridian Analytics Research (fictional)", "employment_id": "EXP-4", "start_date": "2024-01-01", "end_date": "2024-06-30", "project_context": "Fictional internal work programme in analytics, decision support and applied machine learning; not a real client case study.", "problem": "Manual classification delayed incoming requests.", "objective": "Create a workable response to this issue through retrieval systems, explicit review criteria and practical documentation. Agree the boundaries before execution and retain unresolved points for follow-up.", "role_and_ownership": "AI Engineer; owned the stated workstream, not the full organisation or every collaborator contribution.", "contribution": [ "Designed reviewed extraction queues and uncertainty flags.", "Prepared the scope with the commissioning team, identified unresolved inputs and used llm evaluation to turn the brief into a sequenced work package.", "Applied fastapi and vector search while coordinating reviews with the designated owner. Kept decision notes so collaborators could separate facts, assumptions and changes.", "Assembled the handover material, explained open limitations and agreed which items needed further review rather than presenting them as completed." ], "methods": [ "retrieval systems", "LLM evaluation", "FastAPI", "vector search" ], "deliverables": [ "Document intake assistant - scoped brief", "Document intake assistant - reviewed working package", "Document intake assistant - handover and learning summary" ], "review_method": "Reviewed the scoped output against the agreed brief, recorded exceptions and checked that key conclusions could be traced to observations. The review package calls for a evaluation protocol and a named human reviewer.", "outcomes": [ "Illustrative outcome: the team adopted a repeatable approach for document intake assistant, with clearer ownership and reviewable records. This is a fictional qualitative result; no real performance measurement or external acceptance evidence is supplied." ], "metrics": [], "limitations": "Synthetic demonstration only. Examples use synthetic or permissioned data; no claim is made that a model is safe for an untested population. No underlying client documents, independently verified measurements or signed approval records are attached.", "evidence": [ { "id": "E2.1", "title": "Document intake assistant: data-quality and lineage note", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" }, { "id": "E2.2", "title": "Document intake assistant: evaluation protocol", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" }, { "id": "E2.3", "title": "Document intake assistant: model or analysis review", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" } ], "verification_status": "not_verified" }, { "id": "P3", "title": "AI evaluation workbench", "category": "LLM evaluation", "organisation": "Northline Analytics Research (fictional)", "employment_id": "EXP-3", "start_date": "2019-01-01", "end_date": "2019-06-30", "project_context": "Fictional internal work programme in analytics, decision support and applied machine learning; not a real client case study.", "problem": "Model changes were judged through anecdotal examples.", "objective": "Create a workable response to this issue through llm evaluation, explicit review criteria and practical documentation. Agree the boundaries before execution and retain unresolved points for follow-up.", "role_and_ownership": "AI Engineer; owned the stated workstream, not the full organisation or every collaborator contribution.", "contribution": [ "Created versioned test sets and failure-category reporting.", "Prepared the scope with the commissioning team, identified unresolved inputs and used vector search to turn the brief into a sequenced work package.", "Applied tool orchestration and prompt testing while coordinating reviews with the designated owner. Kept decision notes so collaborators could separate facts, assumptions and changes.", "Assembled the handover material, explained open limitations and agreed which items needed further review rather than presenting them as completed." ], "methods": [ "LLM evaluation", "FastAPI", "vector search", "tool orchestration" ], "deliverables": [ "AI evaluation workbench - scoped brief", "AI evaluation workbench - reviewed working package", "AI evaluation workbench - handover and learning summary" ], "review_method": "Reviewed the scoped output against the agreed brief, recorded exceptions and checked that key conclusions could be traced to observations. The review package calls for a model or analysis review and a named human reviewer.", "outcomes": [ "Illustrative outcome: the team adopted a repeatable approach for ai evaluation workbench, with clearer ownership and reviewable records. This is a fictional qualitative result; no real performance measurement or external acceptance evidence is supplied." ], "metrics": [], "limitations": "Synthetic demonstration only. Examples use synthetic or permissioned data; no claim is made that a model is safe for an untested population. No underlying client documents, independently verified measurements or signed approval records are attached.", "evidence": [ { "id": "E3.1", "title": "AI evaluation workbench: data-quality and lineage note", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" }, { "id": "E3.2", "title": "AI evaluation workbench: evaluation protocol", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" }, { "id": "E3.3", "title": "AI evaluation workbench: model or analysis review", "type": "suggested_supporting_artifact", "status": "not_supplied", "url": null, "publication_permission": "not_applicable_to_synthetic_sample" } ], "verification_status": "not_verified" } ], "experience": [ { "id": "EXP-4", "position": "AI Engineer", "career_level": "experienced specialist / workstream owner", "organisation": "Meridian Analytics Research (fictional)", "location": "Pune, India", "start_date": "2022-07-01", "end_date": null, "employment_type": "full-time - fictional record", "scope": "Independent ownership of scoped ai engineer work, coordinating contributors and making review requirements explicit. Includes the first two selected work examples.", "responsibilities": [ "Built retrieval with passage citations and abstention checks.", "Designed reviewed extraction queues and uncertainty flags.", "Led brief clarification and prioritised work using python, retrieval systems and llm evaluation. Raised unresolved constraints before committing to the next stage.", "Coordinated peer reviews and handover preparation; used a data-quality and lineage note to distinguish completed work, assumptions and follow-up needs.", "Supported colleagues with practical examples of fastapi and maintained a concise learning record after important assignments." ], "selected_project_ids": [ "P1", "P2" ], "result_context": "Illustrative career responsibilities. Employer confirmation and underlying work records are not supplied.", "verification_status": "not_verified" }, { "id": "EXP-3", "position": "Senior AI Engineer", "career_level": "senior specialist", "organisation": "Northline Analytics Research (fictional)", "location": "Pune, India", "start_date": "2018-07-01", "end_date": "2022-06-30", "employment_type": "full-time - fictional record", "scope": "Owned defined assignments and supported cross-functional coordination. Developed deeper practice in llm evaluation and fastapi.", "responsibilities": [ "Created versioned test sets and failure-category reporting.", "Translated incoming requirements into a sequenced plan and aligned responsibilities with the project or service owner.", "Applied vector search and tool orchestration to resolve delivery questions while maintaining source and decision notes.", "Introduced reusable working documents and reviewed exceptions with the responsible specialist rather than silently changing scope.", "Prepared a model or analysis review so the next team could understand the work and remaining questions." ], "selected_project_ids": [ "P3" ], "result_context": "Illustrative career responsibilities. Employer confirmation and underlying work records are not supplied.", "verification_status": "not_verified" }, { "id": "EXP-2", "position": "AI Engineer", "career_level": "independent practitioner", "organisation": "Cedarbridge Analytics Research (fictional)", "location": "Pune, India", "start_date": "2015-07-01", "end_date": "2018-06-30", "employment_type": "full-time - fictional record", "scope": "Progressed from supported tasks to independently managed assignments, with review available for unfamiliar or higher-risk decisions.", "responsibilities": [ "Handled recurring work involving python and retrieval systems using a documented preparation and review process.", "Supported document intake assistant by organising inputs, maintaining issue notes and incorporating reviewer feedback.", "Coordinated colleagues and internal stakeholders using concise status updates, clear questions and agreed next steps.", "Improved record consistency through prompt testing and documented handover expectations." ], "selected_project_ids": [], "result_context": "Illustrative career responsibilities. Employer confirmation and underlying work records are not supplied.", "verification_status": "not_verified" }, { "id": "EXP-1", "position": "Assistant AI Engineer", "career_level": "foundation", "organisation": "Cedarbridge Analytics Research (fictional)", "location": "Pune, India", "start_date": "2013-07-01", "end_date": "2015-06-30", "employment_type": "full-time - fictional record", "scope": "Built practical foundations through supervised assignments, routine documentation and feedback from experienced colleagues.", "responsibilities": [ "Assisted with python and llm evaluation within an agreed scope and escalated unfamiliar work.", "Prepared inputs and checked completeness before passing work to the responsible reviewer.", "Maintained task records and learned to communicate assumptions, constraints and observed problems clearly.", "Applied review feedback to subsequent assignments and developed a dependable working routine." ], "selected_project_ids": [], "result_context": "Illustrative career responsibilities. Employer confirmation and underlying work records are not supplied.", "verification_status": "not_verified" } ], "career_achievements": [ { "title": "Grounded knowledge assistant", "description": "Built retrieval with passage citations and abstention checks. The achievement is the described workstream contribution; independent outcome evidence is not supplied.", "project_id": "P1", "verification_status": "not_verified", "metrics": [] }, { "title": "Document intake assistant", "description": "Designed reviewed extraction queues and uncertainty flags. The achievement is the described workstream contribution; independent outcome evidence is not supplied.", "project_id": "P2", "verification_status": "not_verified", "metrics": [] }, { "title": "AI evaluation workbench", "description": "Created versioned test sets and failure-category reporting. The achievement is the described workstream contribution; independent outcome evidence is not supplied.", "project_id": "P3", "verification_status": "not_verified", "metrics": [] } ], "education": [ { "id": "EDU-2", "qualification": "M.Tech in Artificial Intelligence", "institution": "Asterbridge Institute of Professional Studies (fictional institution)", "start_date": "2011-07-01", "end_date": "2013-05-31", "status": "completed - fictional record", "focus": [ "Python", "retrieval systems", "FastAPI" ], "capstone": "Specialist study on grounded knowledge assistant; an illustrative learning project, not a published result.", "verification_status": "not_verified" }, { "id": "EDU-1", "qualification": "B.Tech in Computer Science", "institution": "Cedarhaven College of Applied Studies (fictional institution)", "start_date": "2007-07-01", "end_date": "2011-05-31", "status": "completed - fictional record", "focus": [ "LLM evaluation", "vector search", "tool orchestration" ], "capstone": "Applied coursework in python, documentation and reviewed practical assignments.", "verification_status": "not_verified" } ], "professional_development": [ { "title": "Experiment design practicum", "provider": "Meridian Professional Learning Studio (fictional)", "year": 2023, "learning_focus": "Python and fastapi in the context of ai engineer work.", "application": "Used reflective exercises and a bounded practice example related to grounded knowledge assistant.", "type": "continuing learning - not a licence or certification", "verification_status": "not_verified" }, { "title": "Responsible data handling workshop", "provider": "Meridian Professional Learning Studio (fictional)", "year": 2024, "learning_focus": "Retrieval systems and vector search in the context of ai engineer work.", "application": "Used reflective exercises and a bounded practice example related to document intake assistant.", "type": "continuing learning - not a licence or certification", "verification_status": "not_verified" }, { "title": "Model monitoring case lab", "provider": "Meridian Professional Learning Studio (fictional)", "year": 2025, "learning_focus": "Llm evaluation and tool orchestration in the context of ai engineer work.", "application": "Used reflective exercises and a bounded practice example related to ai evaluation workbench.", "type": "continuing learning - not a licence or certification", "verification_status": "not_verified" } ], "credentials": { "professional_registration": null, "licence_number": null, "issuing_authority": null, "credential_documents": [], "status": "not_provided", "scope_note": "Examples use synthetic or permissioned data; no claim is made that a model is safe for an untested population.", "education_note": "Synthetic qualification and institution names illustrate profile fields only; they are not a validated qualification route or recognised accreditation claim." }, "leadership_and_knowledge_sharing": [ { "title": "Peer learning and practical guidance", "description": "Created short examples on python and fastapi for colleagues. Separated personal preferences from agreed team procedures and recorded useful questions." }, { "title": "Review and handover discipline", "description": "Facilitated practical reviews of document intake assistant, ensuring that unresolved issues retained a named owner rather than disappearing from final presentations." } ], "record_integrity": { "source_status": "synthetic_and_unverified", "actual_outcome_metrics_supplied": false, "references": [], "references_note": "No real referee, endorsement, award, publication, membership or licence is supplied.", "permission_note": "Use for templates, product demonstrations and test data only. Replace fictional claims and remove the demo label only after approval of real candidate information.", "privacy_note": "No actual birth date, street address, government identifier, patient record or private third-party information is included." }, "search_keywords": [ "Python", "retrieval systems", "LLM evaluation", "FastAPI", "vector search", "tool orchestration", "prompt testing", "data access controls", "AI Engineer", "AI, Data & Analytics" ] }