AI Engineer (2+ years, In-Office - Coimbatore)

About the Role
We’re hiring an AI Engineer to join our fast-moving product team and build cutting-edge AI solutions using LLMs, RAG, GraphRAG, and vector databases. You’ll work hands-on with GenAI tools and frameworks to deliver production-grade AI systems for real-world use cases.

This is a mandatory in-office role in Coimbatore, ideal for someone who thrives in a collaborative, high-energy environment and enjoys solving challenging problems with the latest advancements in AI.

What You’ll Do

• Build and deploy RAG/GraphRAG pipelines using LLMs and vector databases.
• Work with tools like LangChain, LlamaIndex, Qdrant, Pinecone, etc.
• Fine-tune, evaluate, and optimize models for production performance.
• Integrate AI into product workflows with scalable APIs.
• Stay updated on recent advancements in GenAI and experiment with them.

What We’re Looking For

• 2+ years of experience in machine learning or applied AI, with recent hands-on work in GenAI frameworks (LLMs, RAG, etc.).
• Strong Python skills and experience with frameworks like PyTorch or TensorFlow.
• Hands-on with LLMs, RAG, embeddings, and vector similarity search.
• Experience with vector databases (e.g., Pinecone, Qdrant, Weaviate).
• Familiar with LangChain, LlamaIndex, or other orchestration tools.
• Must be based in or willing to relocate to Coimbatore (no exceptions).

Nice to Have

• Experience with GraphRAG and knowledge graphs (Neo4j, ArangoDB).
• Familiarity with deploying models on AWS/GCP/Azure.
• Contributions to open source or research in GenAI/LLMs.

Why Join Us?

• Work on exciting AI-first products from scratch.
• Collaborate with a highly motivated team in-person.
• Freedom to experiment with the latest in GenAI.
• Opportunity to grow fast and own key AI systems.