Similar Jobs
See allWhat You’ll Do Day-to-Day:
- Design and implement production-grade RAG pipelines and agentic workflows using Python.
- Build systems that handle real-world "messy" data (PDFs, scanned docs, images, full motion video).
- Ensure they are performant and scalable.
Research & Experimentation:
- Evaluate new models (LLMs, embedding models, object detection).
- Prototype approaches for SBIR/government deliverables.
- Run experiments to prove what actually works.
Must-Haves:
- Proven experience deploying Production RAG pipelines against real-world, messy datasets.
- Deep expertise in Agentic system design (tool-use, multi-agent orchestration).
- Strong Python engineering skills—writing clean, scalable, and maintainable code
Unstructured Technologies
Unstructured is focused on transforming unstructured data into a format usable by LLMs. Their Public Sector team works on high-impact contracts and seek to bridge the gap between custom builds and a scalable product roadmap.