LLM Systems Engineer — AI, LangChain & Production APIs

BayRockLabs; Newark (CA); Hybrid; USD 110,208 - 123,984; Full time

Job summary

A leading product engineering firm in Newark, California is seeking a skilled AI Engineer to design, build, and integrate advanced AI systems powered by large language models (LLMs). The ideal candidate will have strong expertise in Python, experience with LangGraph/LangChain, and proficiency in FastAPI for developing production-grade APIs. This hybrid role offers competitive pay and the opportunity to work on innovative projects in a collaborative environment.

Qualifications

• Strong hands-on experience with LLM-powered systems (e.g., GPT, Claude, LLaMA, Mistral).
• Deep expertise in Python for AI/ML development.
• Proven experience with LangGraph/LangChain for agent workflow orchestration.

Responsibilities

• Design and build advanced AI systems powered by large language models (LLMs).
• Develop and integrate agent workflows using LangGraph/LangChain frameworks.
• Implement production-grade APIs with FastAPI to support scalable deployments.

Skills

LLM-powered systems

Python

LangGraph/LangChain

FastAPI

ML lifecycle management

Cloud platforms (Azure, AWS, or GCP)

Problem-solving skills

Tools

MLOps tools (MLflow, Kubeflow)

Vector databases (Pinecone, Weaviate, FAISS)

Job description

A leading product engineering firm in Newark, California is seeking a skilled AI Engineer to design, build, and integrate advanced AI systems powered by large language models (LLMs). The ideal candidate will have strong expertise in Python, experience with LangGraph/LangChain, and proficiency in FastAPI for developing production-grade APIs. This hybrid role offers competitive pay and the opportunity to work on innovative projects in a collaborative environment.