Description

You will build and ship production-grade GenAI systems, owning the full lifecycle from model integration to user-facing interfaces.

This role is remote.

Responsibilities

• Architect and implement agentic workflows using LangChain and LangGraph, including state graphs, retries, and sub-graphs.
• Design and optimize RAG pipelines with chunking strategies, hybrid retrieval, rerankers, and robust evaluation metrics.
• Deploy and manage models on Vertex AI, handling endpoints, pipelines, vector search, and IAM configurations.
• Build scalable backends in Python (FastAPI) or Node.js and develop React/Next.js frontends for AI-driven applications.
• Implement observability, security, and governance practices, including PII handling, prompt injection defenses, and secret management.

Required Skills

• 7–10+ years of software engineering experience, with 3–5+ years focused on applied ML/GenAI in production.
• Expertise with LangChain and LangGraph for building complex agent architectures.
• Hands-on experience with Google Vertex AI (Foundational models, Endpoints, Pipelines, Vector Search).
• Deep knowledge of vector databases (Pinecone, Weaviate, Milvus, FAISS) and embedding models.
• Strong proficiency in Python (FastAPI) or Node.js, with React/Next.js frontend experience.
• Solid cloud experience on GCP (preferred) or AWS/Azure, plus Docker/Kubernetes and CI/CD.
• Experience with GenAI evaluation tools (RAGAS, G-Eval) and observability platforms (LangSmith, OpenTelemetry).

Preferred Skills

• Knowledge of knowledge graphs (RDF/OWL), retrieval planning, and toolformer/agent patterns.
• Experience with LLM serving/routing, Guardrails, Instructor schemas, and LlamaIndex.

Key Skills

Education

Bachelor's degree