Principal Engineer - Context Engineering & LLM Optimization

What you'll do

• Owns portfolio-level engineering strategy, architecture decisions, technical reviews, and reusable standards across teams.
• Designs LLM context management, prompt architecture, retrieval orchestration, grounding, memory, and tool-use patterns.
• Leads end-to-end testing and LLM evaluation; mentors engineers and balances quality, security, reliability, scalability, and cost.

What they ask for

• 10+ years of software, data, platform, or AI engineering experience; 5+ years designing large-scale enterprise systems; 2+ years working with LLM, RAG, vector search, semantic search, or AI platform capabilities.
• Production LLM, RAG, or AI assistant architecture experience, including prompt and context design, context-window management, grounding, and response evaluation.
• Experience in regulated, security-conscious, or enterprise-scale environments and leading architecture across multiple engineering teams.
• Bachelor’s degree in Computer Science, Engineering, Information Systems, Applied Mathematics, or a related technical field.

Nice to have

• Experience with agentic workflows, multi-agent orchestration, function calling, or tool-augmented reasoning.
• Experience with prompt injection mitigation, token optimization, contextual compression, or enterprise memory patterns.

Tools

OpenAI, Azure OpenAI, Anthropic, Google Gemini, Meta Llama, RAG, vector search, embeddings

AI focus

Enterprise LLM and RAG engineering: context and prompt design, retrieval orchestration, grounding, tool use, memory, safety, and evaluation to improve answer quality and token efficiency.