AI Engineer - LLM Agents

Job Title: AI Engineer - LLM Agents

Experience: 1-2 years

Job Location: Greater Noida

We are looking for an AI Engineer with 1–2 years of experience in building production-ready LLM agents using TypeScript/Node.js. The role involves developing AI agents, implementing RAG pipelines, document understanding, tool orchestration, and evaluation frameworks. The ideal candidate should have hands-on experience with AI Agents SDK, PostgreSQL, embeddings, prompt engineering, and guardrails, along with a strong focus on building accurate, secure, and scalable AI solutions.  

• Build and own the core of Agent using the AI Agents SDK (TypeScript) and the hosted Agents API- agent instructions, tool orchestration, and per-conversation sessions.
• Design the agent’s decision-making so it reliably understands requests in Chat and selects the correct tools to act on them.
• Build document-understanding pipelines that extract requirements from files in any format, including scanned documents and images via OpenAI vision.
• Implement retrieval (RAG) using hybrid search - pgvector embeddings plus PostgreSQL full-text - with sound chunking, versioning, and relevance tuning.
• Define and maintain the AI evaluation framework: build eval sets from past projects, set per-wave accuracy targets, and enforce the evaluation gate in CI so quality never regresses.
• Implement guardrails and prompt-injection defenses, ensuring all documents and messages are treated as data, never as instructions, and that the model performs language tasks only - never computing numbers, dates, or permissions.
• Deliver multilingual understanding, including mixed-language conversations, with consistent, correct responses.
• Continuously review agent accuracy against saved guidance, and improve the system from real usage.

• 1–2 years of software engineering experience, including real, production-shipped work on LLM agents with tool/function calling (AI Agents SDK, LangGraph, or equivalent).
• Strong TypeScript / Node.js proficiency, or deep JavaScript experience with genuine willingness to work in TypeScript (strict mode). Python-only candidates are not a fit for this role.
• Hands-on RAG expertise: embeddings, vector search (pgvector or similar), chunking, and retrieval-quality optimization.
• A rigorous, demonstrable approach to evaluation and guardrails - able to explain how agent accuracy is measured and how hallucinations and prompt injection are prevented.
• Working knowledge of PostgreSQL and API integration.
• Strong analytical skills, clear written communication, and the ability to work closely with backend team.
• Nice to have: OpenAI vision/classification pipelines, MCP (Model Context Protocol) experience.