Full-time
0 - 2 Years
₹10,00,000 - ₹18,00,000 / yr
Role Overview
We are pioneering next-generation enterprise retrieval-augmented generation (RAG) pipelines. In this role, you will evaluate embedding models, connect vector stores, and build autonomous agent workflows for production applications.
Requirements & Tech Competencies
• Deep understanding of Transformers, prompt engineering, and LLM orchestration (LangChain, LlamaIndex).
• Hands-on coding in Python with FastAPI or Django backends.
• Experience with vector databases (Chroma, Pinecone, or pgvector).
• Familiarity with fine-tuning and evaluation metrics for generative models.
Technical Skills & Stack
Python
LangChain
OpenAI APIs
PyTorch
Vector DBs
ChromaDB
Verified Opening via Wellfound
Listing synchronized directly from Wellfound. Click below to access the application portal.
Open Application Form