Senior AI Engineer (Generative AI & Agentic Systems)

Genesis10•Pennington, NJ

About The Position

Genesis10 is seeking a Senior AI Engineer specializing in Generative AI and agentic systems for a 12+ month contract position with a global financial institution in Pennington, New Jersey. The engineer will design, build, and scale production-grade large language model (LLM) applications and enterprise solutions using modern agentic frameworks. The role focuses on architecting and optimizing Retrieval-Augmented Generation (RAG) pipelines; developing stateful multi-agent systems and autonomous workflows; and integrating, tracing, evaluating, debugging, and monitoring LLM applications. The engineer will connect agents and workflows to external data sources, enterprise APIs, vector databases, and developer tools, and optimize token usage, latency, and operating costs while preserving quality and accuracy. The position is offered through Genesis10, and candidates must be available and ready to work directly as Genesis10 employees. The stated pay range is $55.06–$63.06 per hour. Benefits for contract roles include a behavioral health platform; medical, dental, and vision coverage; a health savings account; voluntary hospital indemnity, critical illness, accident, and term life insurance; 401(k); sick pay in applicable locations; and commuter benefits in specified locations.

Requirements

Advanced, production-level Python proficiency, including asyncio, design patterns, profiling, and testing.
Hands-on production experience with one or more of LangChain, LangGraph, LangSmith, or Deepagents.
Deep working knowledge of RAG pipelines, prompt engineering strategies, and vector database integration.
Familiarity with major LLM providers, including OpenAI, Anthropic, and open-source models via Hugging Face or Ollama.
Familiarity with function-calling and tool-use architectures.
Experience with Git, CI/CD pipelines, Docker, and cloud environments such as AWS, GCP, or Azure.
Must be available and ready to work directly as a Genesis10 employee.

Responsibilities

Design, implement, and optimize RAG architectures, including custom chunking, hybrid search, embedding optimization, and reranking.
Develop complex, stateful multi-agent systems and autonomous workflows using frameworks such as LangGraph and Deepagents.
Use LangChain for LLM integration and LangSmith for tracing, evaluation, debugging, and production performance monitoring.
Write clean, modular, efficient, maintainable Python code using asynchronous programming, strict typing, and robust error handling.
Integrate LLM agents and workflows with external data sources, enterprise APIs, vector databases, and developer tools, including Model Context Protocol integrations where applicable.
Optimize token usage, latency, and operational costs without compromising response quality or accuracy.