As a Senior AI Developer, the contractor will lead the end-to-end design, development, deployment, and continuous improvement of autonomous AI workflows and intelligent agents. The role requires strong hands-on engineering capability in Python and Java, deep experience with TensorFlow and PyTorch, and practical delivery experience across modern agentic AI frameworks such as LangChain, LangGraph, CrewAI, and AutoGen. The developer will integrate LLMs such as GPT, Claude, Llama, and Mistral into multi-agent orchestration pipelines, implement RAG solutions using vector stores such as Milvus, Pinecone, and Azure AI Search, and embed AI agents into CI/CD, Docker/Kubernetes, and infrastructure-as-code environments.
The role will also champion Model Context Protocol adoption by authoring MCP servers and clients so AI agents can securely interface with enterprise systems, tools, and data stores through bidirectional context exchange. Expertise in Harness and Context Engineering.
This role offers the opportunity to work on cutting-edge AI agent engineering, including LLM orchestration, MCP adoption, production RAG systems, long-term memory, observability, and enterprise-grade AI workflow automation. The candidate will gain experience building scalable GenAI solutions that connect directly to enterprise systems and improve software engineering productivity.
8+ years of hands-on AI/ML development experience and custom app development. Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, or a related field. Required background includes Python and Java development, AI/ML frameworks, agentic AI frameworks, LLM integration, RAG/vector databases, CI/CD, Docker/Kubernetes, observability, prompt engineering, function calling, memory management, and production AI deployment.
Must have:
Agentic AI development: hands-on experience designing, building, and deploying AI agents using LangChain, LangGraph, CrewAI, AutoGen, or similar frameworks. Expertise in Architecture and Design for enterprise applications.
LLM/RAG engineering: integration of LLMs, prompt strategies, function calling, vector stores, embeddings, RAG pipelines, and long-term memory patterns.
Production AI engineering: strong Python/Java, TensorFlow/PyTorch, CI/CD, Docker/Kubernetes, infrastructure as code, observability, logging, monitoring, and debugging.