Back
Niche LLM agent expertise and seniority reduce applicant density.
Highly specialized LLM agent, prompt-engineering, and evaluation experience limits cross-industry transferability.
Explicit 8+ years, 3+ lead experience and many mandatory LLM/stack requirements enforce strict filtering.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Own end-to-end design and implementation of audit capabilities including data models, prompt structures, API, persistence, and React UI.
Lead prompt engineering and agent design for verdict-issuing and insight agents, enforcing platform standards and conducting code reviews.
Collaborate with audit teams to translate SOPs into machine-readable control logic and manage accuracy/hallucination control programs for LLM-powered systems.
8+ years professional software engineering experience, including 3+ years in a hands-on technical lead role.
Strong Python (3.11+) skills with experience in FastAPI or equivalent async frameworks, Pydantic v2, asyncio, SQLAlchemy/ORM, and Postgres.
Hands-on experience building production AI agents using frameworks like Google ADK, LangGraph, LlamaIndex, or OpenAI Assistants with practical prompt engineering on frontier LLMs (e.g., GPT-4, Claude).
Experience with React + TypeScript at a review and contribution level, containerized deployments (Docker, Cloud Run/GKE), Git workflows, and running accuracy/regression programs for LLM systems.
Technically hands-on lead capable of architecting and coding complex AI agent systems, including schema design and orchestration.
Experienced in prompt engineering and production deployment of LLM-powered audit or compliance tooling with emphasis on accuracy and hallucination controls.
Collaborator who can translate business SOPs into technical control logic and work cross-functionally with audit teams and security/review panels.