Description

You will build and productionize agentic AI systems using Vertex AI, owning the entire delivery lifecycle from data ingestion through to deployment.

Responsibilities

• Design and implement Retrieval Augmented Generation (RAG) pipelines on Google Cloud / Vertex AI, covering chunking, embeddings, retrieval, and grounding.
• Build complex agentic workflows, managing tool use, planning, reflection, and structured outputs using Python.
• Integrate agents with Vector Databases (e.g., Pinecone, pgvector) and Graph Databases (e.g., Neo4j) for enhanced retrieval.
• Define and execute system evaluation (retrieval metrics, answer quality, hallucination checks) and iterate on system quality.
• Ship solutions to production, ensuring API stability, monitoring, cost optimization, and CI/CD adherence.

Required Skills

• 10+ years of professional experience in software development.
• Strong proficiency in Python, including clean architecture, async programming, typing, and testing.
• Proven experience building production-grade RAG solutions, including hybrid search and chunking strategies.
• Hands-on experience with Vertex AI and core GCP fundamentals (IAM, Cloud Run/GKE).
• Experience implementing agentic frameworks (e.g., LangGraph/LangChain, AutoGen) and function calling patterns.
• Solid knowledge of vector search concepts and production use of at least one vector database.
• Familiarity with graph data modeling and querying languages (Cypher/Gremlin basics).
• Strong engineering practices: code reviews, telemetry implementation, and security-by-design.

Key Skills

Education

Any Graduate