Description

You will own end-to-end delivery of Vertex AI–based RAG systems, from ingestion through retrieval, agent orchestration, evaluation, and deployment.

This role is on-site.

Responsibilities

• Design and implement RAG pipelines on Google Cloud/Vertex AI, including chunking, embeddings, indexing, retrieval, reranking, and grounding.
• Build agentic workflows using Python-first frameworks, focusing on tool use, planning, reflection, guardrails, and structured outputs.
• Integrate agents with graph databases (Neo4j, JanusGraph, Neptune) and vector databases (Vertex Vector Search, Pinecone, Weaviate, Milvus, pgvector).
• Create robust data ingestion and ETL processes for PDFs, documents, webpages, and internal sources, implementing metadata strategies and access control.
• Define and run evaluations for retrieval metrics, answer quality, and hallucination checks, shipping to production with monitoring, CI/CD, and security best practices.

Required Skills

• Strong Python proficiency with clean architecture, async programming, testing, typing, and packaging.
• Proven experience building RAG solutions, including hybrid search, reranking, chunking strategies, embeddings, and prompt/schema design.
• Hands-on experience with Vertex AI and GCP fundamentals, including IAM, logging/monitoring, Cloud Run, GKE, and storage.
• Experience with agentic frameworks such as LangGraph, LangChain, LlamaIndex, Semantic Kernel, or AutoGen, plus tool/function calling patterns.
• Solid knowledge of vector search concepts and at least one vector database in production.
• Comfortable with graph data modeling and querying (Cypher, Gremlin, or SPARQL basics).
• Strong engineering practices including code reviews, testing, telemetry, secure-by-design principles, and reliability.
• 10+ years of professional engineering experience.

Preferred Skills

• Knowledge graphs for RAG, including entity linking, graph traversal, and retrieval fusion.
• Experience with streaming/messaging (Pub/Sub, Kafka), Document AI, and multilingual retrieval.
• Familiarity with evaluation tooling (RAGAS, TruLens) and frontend integration (React/Next.js).

Key Skills

Education

Any Graduate