AI / LLM Engineer
Bengaluru2+ Years1 Open
Ship LLM apps, agents and RAG pipelines into real products.
Roles and responsibilities
- Build LLM-backed features — assistants, agents and automations — into products customers use daily.
- Design and tune retrieval pipelines: chunking, embeddings, vector search and re-ranking.
- Evaluate output quality with real test sets rather than one-off spot checks.
- Keep latency and token cost inside budget without giving up answer quality.
- Work with product and engineering to decide what genuinely benefits from a model and what does not.
Skills and qualifications
- 2+ years in software engineering, with hands-on LLM application work.
- Practical experience with at least one major model provider's API and its tool-use patterns.
- Solid Python, plus enough JavaScript to integrate with our front ends.
- Understanding of embeddings, vector stores and the failure modes of retrieval.
- Healthy scepticism about model output and a habit of measuring instead of assuming.
Educational qualifications
B.E / B.Tech / M.Tech or equivalent
Skills required
LLM APIs, RAG, Vector DBs, Python, Prompt Engineering
Job & employment type
On-site · Permanent
