← All open roles
AI & DataRemote / Ahmedabadfull-time
AI / ML Engineer
We are expanding our AI practice and need an engineer who can take LLM-powered features from prototype to production. You will design RAG pipelines, fine-tune models, and build the infrastructure that makes AI features reliable, cost-efficient, and auditable.
What you'll do
- Design and implement AI features for client products
- Build and maintain RAG pipelines backed by client data sources
- Evaluate model outputs and build automated quality checks
- Work with engineering leads to integrate AI into existing Node.js backends
- Stay current with the fast-moving LLM landscape and bring recommendations to the team
What we're looking for
- 2+ years of hands-on experience with LLM APIs (OpenAI, Anthropic, Gemini)
- Practical experience building RAG pipelines (chunking, embedding, reranking)
- Python proficiency; familiarity with LangChain or LlamaIndex
- Understanding of vector databases (Pinecone, Weaviate, pgvector)
- Ability to reason about token costs and latency trade-offs