Pay Growth
?
out of 5
Not enough data
Not enough info to score pay or growth
Agentic AI Lead
Job
Galent
Fanwood, NJ (In Person)
Full-Time
Review key factors to help you decide if the role fits your goals.
Job Security
?
out of 5
Not enough data
Calculating job security score...
Total Score
100
out of 100
Average of individual scores
Skill Insights
Compare your current skills to what this opportunity needs—we'll show you what you already have and what could strengthen your application.
Job Description
Agentic AI Lead at Galent Agentic AI Lead at Galent in Fanwood, New Jersey Posted in 1 day ago.
What you'll doDesign and implement RAG pipelines on Google Cloud / Vertex AI (chunking, embeddings, indexing, retrieval, reranking, grounding ).Build agentic workflows (tool use, planning, reflection/guardrails, structured outputs) using Python-first framework s.
Integrate agents with Graph DBs (e.g., Neo4j, JanusGraph, Neptune) and Vector DBs (e.g., Vertex Vector Search, Pinecone, Weaviate, Milvus, pgvector ).Create robust data ingestion/ETL from PDFs, docs, webpages, and internal sources; implement metadata strategy and access contro l.
Define and run evaluation (retrieval metrics, answer quality, hallucination/grounding checks), and improve system quality iterativel y.
Ship to production: APIs, monitoring/observability, cost/performance optimization, CI/CD, and security best practice s.
Must-have skil lsStrong Python (clean architecture, async, testing, typing, packaging ).Proven experience building RAG solutions (hybrid search, reranking, chunking strategies, embeddings, prompt + schema design ).Hands-on with Vertex AI and GCP fundamentals (IAM, logging/monitoring, Cloud Run/GKE, storage ).Experience with at least one agentic framework (e.g., LangGraph/LangChain, LlamaIndex, Semantic Kernel, AutoGen) and tool/function calling pattern s.
Solid knowledge of vector search concepts and at least one vector DB in productio n.
Comfortable with graph data modeling and graph querying (Cypher/Gremlin/SPARQL basics ).
Nice-to-ha veKnowledge graphs for RAG (entity linking, graph traversal + retrieval fusion ).Streaming/messaging (Pub/Sub, Kafka), document pipelines (Document AI), and multilingual retrieva l.
Experience with evaluation tooling (RAGAS, TruLens, custom eval harnesses), prompt/version managemen t.
Frontend integration (basic React/Next.js) or platform enablement (internal developer tooling ). We are an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex (including pregnancy, sexual orientation, or gender identity), national origin, citizenship status, age, disability, genetic information, protected veteran status, or any other characteristic protected by applicable law.
Type:
full-timeJob Description:
Role :
Agentic AI Lead (Python) - Vertex AI RAG +Graph/Vector Datastores Location :
Berkeley Heights, NJ (All 5 Days a week Onsite)Duration :
Full Time Role summa ryWe're looking for a strong agentic AI developer who can build and productionize Vertex AI-based RAG systems (Vertex AI Search / Vertex AI RAG patterns), design reliable tool-using agents, and work comfortably with vector databases and graph databases. You'll own end-to-end delivery: ingestion ? retrieval ? agent orchestration ? evaluation ? deploymen t.What you'll doDesign and implement RAG pipelines on Google Cloud / Vertex AI (chunking, embeddings, indexing, retrieval, reranking, grounding ).Build agentic workflows (tool use, planning, reflection/guardrails, structured outputs) using Python-first framework s.
Integrate agents with Graph DBs (e.g., Neo4j, JanusGraph, Neptune) and Vector DBs (e.g., Vertex Vector Search, Pinecone, Weaviate, Milvus, pgvector ).Create robust data ingestion/ETL from PDFs, docs, webpages, and internal sources; implement metadata strategy and access contro l.
Define and run evaluation (retrieval metrics, answer quality, hallucination/grounding checks), and improve system quality iterativel y.
Ship to production: APIs, monitoring/observability, cost/performance optimization, CI/CD, and security best practice s.
Must-have skil lsStrong Python (clean architecture, async, testing, typing, packaging ).Proven experience building RAG solutions (hybrid search, reranking, chunking strategies, embeddings, prompt + schema design ).Hands-on with Vertex AI and GCP fundamentals (IAM, logging/monitoring, Cloud Run/GKE, storage ).Experience with at least one agentic framework (e.g., LangGraph/LangChain, LlamaIndex, Semantic Kernel, AutoGen) and tool/function calling pattern s.
Solid knowledge of vector search concepts and at least one vector DB in productio n.
Comfortable with graph data modeling and graph querying (Cypher/Gremlin/SPARQL basics ).
Strong engineering practices:
code reviews, testing, telemetry, secure-by-design, reliability mindse t.Nice-to-ha veKnowledge graphs for RAG (entity linking, graph traversal + retrieval fusion ).Streaming/messaging (Pub/Sub, Kafka), document pipelines (Document AI), and multilingual retrieva l.
Experience with evaluation tooling (RAGAS, TruLens, custom eval harnesses), prompt/version managemen t.
Frontend integration (basic React/Next.js) or platform enablement (internal developer tooling ). We are an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex (including pregnancy, sexual orientation, or gender identity), national origin, citizenship status, age, disability, genetic information, protected veteran status, or any other characteristic protected by applicable law.