Description

You will design and implement production-grade AI systems, focusing on RAG pipelines, multi-agent workflows, and scalable data engineering.

This role is hybrid.

Responsibilities

• Build end-to-end Retrieval-Augmented Generation (RAG) pipelines, extracting and processing data from PDFs, wikis, and enterprise sources.
• Develop agentic workflows using LangGraph, Agno, or Google ADK, managing state and inter-agent communication.
• Design hybrid search systems with vector databases (Qdrant, Pinecone, Weaviate), optimizing indexing strategies like HNSW.
• Construct scalable ETL pipelines to transform unstructured data into structured, searchable knowledge bases.
• Containerize applications with Docker and deploy low-latency AI services, ensuring reliability and performance in production.

Required Skills

• 5+ years of experience with Python, including Asyncio, FastAPI, and Pydantic.
• Hands-on experience building RAG systems and working with LLM-based applications.
• Proficiency with agentic AI frameworks such as LangGraph, Agno, or Google ADK.
• Experience with vector databases including Qdrant, Weaviate, or Pinecone.
• Strong understanding of similarity search, embeddings, and HNSW indexing.
• Background in processing and structuring unstructured data sources.
• Familiarity with production deployment practices and data governance standards.

Key Skills

Education

Bachelor's degree