Skip to main content
Saxon Global

AI Engineer

Saxon Global New Jersey, United States 16 days ago

$63 - $63 USD hourly

We are seeking an Advanced Python Engineer with specialized expertise in Generative AI orchestration, multi-agent workflows, and Retrieval-Augmented Generation (RAG) systems. In this role, you will design, build, and scale production-grade LLM applications, leveraging modern agentic frameworks to power intelligent enterprise solutions.

Responsibilities:

  • Architect & Scale RAG Pipelines: Design, implement, and optimize advanced Retrieval-Augmented Generation (RAG) architectures, including custom chunking, hybrid search, embedding optimization, and reranking mechanisms
  • Build Agentic Workflows: Develop complex, stateful multi-agent systems and autonomous workflows using frameworks such as LangGraph and Deepagents
  • Orchestrate & Monitor: Utilize LangChain for robust LLM integration and LangSmith for tracing, evaluation, debugging, and performance monitoring of production LLM pipelines
  • Advanced Python Engineering: Write clean, modular, highly efficient, and maintainable Python code adhering to modern standards (asynchronous programming, strict typing, and robust error handling)
  • System Integration: Connect LLM agents and workflows with external data sources, enterprise APIs, vector databases, and developer tooling (including Model Context Protocol integrations where applicable)
  • Performance & Cost Optimization: Optimize token usage, latency, and operational costs across LLM-driven applications without compromising response quality or accuracy

Requirements:

  • Core Programming: Advanced, production-level proficiency in Python (asyncio, design patterns, profiling, and testing)
  • Orchestration & Agent Frameworks: Demonstrated hands-on production experience with one or more of the following:
    • LangChain
    • LangGraph
    • LangSmith
    • Deepagents
  • RAG & Vector Search: Deep working knowledge of RAG pipelines, prompt engineering strategies, and integration with vector databases (e.g., Pinecone, Weaviate, Milvus, Qdrant, or pgvector)
  • LLM Ecosystem: Familiarity with major LLM providers (OpenAI, Anthropic, open-source models via Hugging Face/Ollama) and function-calling / tool-use architectures
  • Software Engineering Best Practices: Experience with Git, CI/CD pipelines, containerization (Docker), and cloud environments (AWS, GCP, or Azure)
Apply now
New Jersey, United States
On-site
$63 - $63 USD hourly
16 days ago

Share this job