You build the AI features clients put in front of real users: LLM applications, retrieval-augmented generation (RAG) systems and AI agents, from the first prototype to production.
What you will do
- Design and build LLM applications, RAG pipelines and AI agents
- Choose models, prompts, retrieval and tools for each use case, and explain the trade-offs to the team and the client
- Build evaluation sets and track quality, latency and cost with every change
- Work with backend and frontend engineers to ship features into production
- Monitor live systems and improve them from real usage
What you bring
- 2+ years of software engineering with Python
- Hands-on work with LLM APIs (OpenAI, Anthropic Claude, Google Gemini or open models)
- Experience with embeddings, vector databases and retrieval
- Comfort with REST APIs, Git and writing tests
- Clear written English for working with remote teams and clients
Good to have
- LangChain, LangGraph or LlamaIndex
- Fine-tuning, PyTorch or Hugging Face
- Deploying models and services on AWS, Azure or Google Cloud
How we work
Remote, from anywhere in India, 9 am to 6 pm IST. You work in a small team with a lead engineer, ship in short cycles and review each other's code. Projects come from clients in India and around the world.