Senior AI Systems Engineer (RAG)

We’re seeking a Senior AI Systems Engineer with deep expertise in RAG, information retrieval, and LLM context engineering. This position focuses on LLMS receive the right information, in the right format, at the right time. You’ll take technical ownership of the systems responsible for identifying relevant information, retrieving it efficiently, and constructing high-quality context for downstream language models. The ideal candidate has built and optimized these systems in production, and understands the limitations of modern LLMs.

What You’ll Do

• Design and Optimize Retrieval Systems: Architect and improve RAG pipelines supporting complex AI applications. Develop sophisticated retrieval strategies using semantic search, optimize document ingestion, indexing, and retrieval across large datasets.
• Advance LLM Context Engineering: Design intelligent context assembly strategies that determine which information reaches the model and how it’s organized. Optimize context selection, ordering, compression, and token utilization to improve LLM response quality.
• Build Evaluation and Measurement Frameworks: Develop repeatable evaluation pipelines to measure retrieval relevance, answer quality, factual grounding, and system performance. Establish benchmarks and datasets to identify regressions and guide technical improvements.
• Engineer Secure, Production-Ready AI Systems: Implement retrieval architecture, ensure retrieved content is accurate, traceable, and appropriately grounded in source material.

• Strong software engineering background with hands-on experience developing and maintaining production AI systems.
• Demonstrated expertise in RAG, information retrieval, semantic search, or LLM context engineering.
• Experience designing and operating retrieval or context management systems serving real users in production.
• Deep understanding of document chunking, embedding strategies, vector search, hybrid retrieval, indexing, and re-ranking.
• Strong knowledge of LLM behavior, including context-window limitations, information ordering, token management, and grounding.
• Ability to measure and optimize tradeoffs involving quality, latency, scalability, and infrastructure cost.
• Understanding of document-level authorization, data isolation, and secure information retrieval.

This Jobot Job is hosted by: Grant Greenhalgh Are you a fit? Easy Apply now by clicking the “Apply Now” button and sending us your resume. Salary: $170,000 - $200,000 per year

A bit about us:

We’re an early-stage AI startup on a mission to redefine how users interact with intelligent systems. We’re building something brand new and we’re looking for talent to help us scale our platform services.

Why join us?

• Fully Remote
• Well-funded
• Senior team of proven engineers
• Autonomy and upward mobility
• Competitive compensation
• Lucrative Equity
• Great healthcare benefits