Overview
This is an exciting opportunity for a Senior AI Engineer / LLM Engineer to work in a dynamic, hybrid environment focused on developing reliable production-grade AI systems. The successful contractor will collaborate with a team to effectively implement emerging technologies in Generative AI, ensuring they perform optimally in real-world applications while solving complex engineering challenges in deployment.
Responsibilities
- Design and build advanced AI applications utilizing LLMs and API integrations.
- Develop retrieval-augmented generation (RAG) systems and manage vector and graph databases.
- Execute prompt engineering for enhanced AI performance.
- Implement multi-agent workflows and facilitate tool calling and agent handoffs.
- Establish AI evaluation and observability frameworks to monitor system effectiveness.
- Ensure reliability and guardrails for AI systems deployed at scale.
- Create and maintain production APIs and data pipelines.
- Address engineering challenges related to accuracy, reliability, latency, and cost in non-deterministic AI systems.
Requirements
- Demonstrable experience in LLM application development and generative AI technologies.
- Proficiency in Python or a modern programming language.
- Strong background in RAG and prompt engineering methodologies.
- Experience in building AI agents and managing agentic workflows.
- Familiarity with vector databases and knowledge graphs.
- Solid understanding of production API development and cloud platforms (AWS, Azure, GCP).
- Experience with AI evaluation and monitoring practices.
- Prior work experience in regulated industries is a plus, especially focusing on responsible AI practices.