Generative AI / Agentic AI Engineer

Experience : 2+ Years

Employment Type : Full-time

Position Overview :

We are building next-generation Agentic AI systems designed for real-world production deployment - moving beyond proof-of-concepts (POCs) to scale complex multi-agent architectures, advanced RAG pipelines, and enterprise LLMOps.

Key Responsibilities :

- RAG & Knowledge Retrieval : Design and deploy end-to-end RAG pipelines (ingestion, chunking, embeddings, hybrid retrieval, reranking) and Graph RAG / Knowledge Graph-based retrieval systems.

- Multi-Agent Workflows : Architect scalable multi-agent systems featuring tool/API integration, persistent memory, guardrails, and human-in-the-loop governance.

- Optimization & Performance : Drive latency, cost, and scale optimizations through semantic caching, model routing, and token usage optimization.

- Observability & Evaluation : Build robust tracing, evaluation, and monitoring frameworks for LLMs and agentic workflows.

Required Qualifications & Skills :

- Experience : 2+ years of hands-on experience building GenAI/LLM applications and taking them from POC to production.

- Core Tech Stack : High proficiency in Python and frameworks such as LangChain, LangGraph, LlamaIndex, Semantic Kernel, or AutoGen.

- APIs & Vector DBs : Experience with Vector Databases and LLM integrations (OpenAI, Azure OpenAI, Anthropic, Gemini, or open-source models).

- Production Operations : Solid grasp of hallucination reduction techniques, system guardrails, observability tools, and cost tuning.

Preferred Qualifications : Educational background from premier engineering institutes (IIT, IISc, BITS, or NIT).