Senior AI Engineer (Generative AI & Agentic Systems)

Genesis10 • Pennington, NJ

2d

About The Position

Genesis10 is seeking a Senior AI Engineer specializing in Generative AI and agentic systems for a 12+ month contract with a global financial institution in Pennington, New Jersey. The role focuses on designing, building, and scaling production-grade LLM applications using advanced Python, Generative AI orchestration, multi-agent workflows, and Retrieval-Augmented Generation (RAG) systems.

The engineer will develop RAG pipelines and stateful multi-agent workflows, integrate LLMs with enterprise data and tools, and use observability and evaluation tools to monitor production systems. The role also involves improving token usage, latency, and operational costs while maintaining response quality and accuracy. Candidates must be available to work directly as Genesis10 employees.

Requirements

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

Responsibilities

• Architect and scale RAG pipelines, including custom chunking, hybrid search, embedding optimization, and reranking.
• Build 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 performance monitoring of production LLM pipelines.
• Write clean, modular, efficient, maintainable Python code using modern standards, including asynchronous programming, strict typing, and robust error handling.
• Connect LLM agents and workflows with external data sources, enterprise APIs, vector databases, and developer tooling.
• Optimize token usage, latency, and operational costs across LLM applications without compromising response quality or accuracy.

Benefits

• Behavioral Health Platform
• Medical insurance
• Dental insurance
• Vision insurance
• Health Savings Account
• Voluntary Hospital Indemnity, Critical Illness, and Accident coverage
• Voluntary Term Life Insurance
• 401(k)
• Sick pay for applicable states and municipalities
• Commuter benefits in Dallas, NYC, San Francisco, and Illinois

What This Job Offers

• Career Level: Senior
• Education Level: No Education Listed