Back
Senior, niche LLM-agent skillset lowers competition despite Mumbai metro and recognizable employer.
Highly domain-specific LLM, agent, and compliance expertise limits cross-industry transferability.
Explicit 8+ years, mandatory technical-lead and specialized LLM/platform stack impose high shortlisting strictness.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own the end-to-end design and architecture of audit capabilities including data model, prompt engineering, API, persistence, and React UI.
Lead prompt engineering and agent design for verdict-issuing and insight agents with detailed control over output schemas, tool-use, and hallucination mitigation.
Lead code reviews enforcing platform standards and partner with audit teams to translate SOPs into machine-readable control logic while overseeing accuracy and validation programs.
8+ years professional software engineering experience, with 3+ years in a technical lead role.
Strong Python (3.11+) skills including FastAPI or async frameworks, Pydantic v2, asyncio, ORM like SQLAlchemy, and Postgres.
Hands-on experience building production AI agents with frameworks such as Google ADK, LangGraph, LlamaIndex, or OpenAI Assistants.
Experience with prompt engineering on frontier LLMs (e.g., Gemini 2.5/3.x, Claude, GPT-4-class) and React + TypeScript competent for code reviews and contributions.
Experienced in architecting and coding complex AI agent systems with direct accountability for prompt engineering and hallucination control.
Capable of enforcing strict code quality standards and operationalizing evaluation programs for LLM-powered systems.
Able to collaborate cross-functionally with audit teams to translate business controls into technical implementations and make build/integration decisions.