Open position
Generative AI Engineer (LLM and RAG)
Remote (worldwide)Full-time0-2 years experience₹5 to ₹10 LPA
We build LLM applications, RAG pipelines, and agent systems, and we teach others how to do the same. You will prototype and ship generative AI features, work with models from OpenAI, Anthropic, Gemini, and Ollama, and turn what you learn into examples for our courses and products like SideSense Pro and TypeFlow.
What you will do
- Build RAG pipelines with embeddings, vector stores, and rerankers
- Prototype agents and tool-calling workflows with LangGraph
- Integrate hosted and local models: OpenAI, Anthropic, Gemini, Ollama
- Evaluate output quality and iterate on prompts and retrieval
- Support AI features in SideSense Pro and TypeFlow
What we look for
- 0 to 2 years of experience; hands-on LLM projects matter more than titles
- Solid Python and comfort calling and debugging APIs
- Understanding of embeddings, retrieval, and context windows
- At least one built RAG or agent project you can walk us through
- Appetite to keep up with a field that changes monthly
Nice to have
- Fine-tuning or evaluation experience
- Open-source contributions to LLM tooling
- Familiarity with our LangChain or LangGraph courses
Skills
PythonLangChainLangGraphRAGVector databasesPrompt engineering
Apply for this position
Not the right role? See all open positions