Description :

AI Engineer Agents, RAG Systems & Model Fine-Tuning

Experience : 4+ years total, including 2+ years in AI Engineering

Role Type : Full-time

Location : Gurugram

Role Overview :

We are hiring an AI Engineer experienced in building AI agents, RAG systems, and fine-tuning open-weights models. The ideal candidate can design multi-step agent workflows, build robust retrieval pipelines, and adapt models for enterprise use cases.

Responsibilities :

- Design and build agent workflows with reasoning, tool use, context switching, and state management.

- Develop robust RAG architectures including ingestion, indexing, retrieval, ranking, and augmentation.

- Fine-tune open-weights LLMs using LoRA, QLoRA, PEFT, SFT, DPO or similar techniques.

- Integrate agents with APIs, databases, and enterprise systems.

- Build evaluation pipelines for accuracy, grounding, latency, and hallucination control.

- Optimize embeddings, prompts, context windows, and overall workflow performance.

- Collaborate with product and backend teams to deliver end-to-end AI solutions.

Required Skills :

- 2+ years of hands-on AI Engineering experience, including agents or RAG systems.

- Strong Python development skills.

- Experience with agent frameworks (LangChain, LlamaIndex, AutoGen, CrewAI).

- Solid understanding of vector databases (FAISS, Chroma, Pinecone, Weaviate, Elastic).

- Hands-on expertise with open-weights LLMs (Llama, Qwen, Mixtral, etc.).

- Experience with fine-tuning pipelines and model evaluation.

- Understanding of distributed processing and cloud environments.

Nice to Have :

- Experience integrating multi-agent systems.

- Familiarity with evaluation sets, guardrails, grounding validators.

- Knowledge of Azure/AWS deployment for RAG and agent systems.