Unstructured is focused on transforming messy, unstructured data into usable formats for LLMs. They are seeking an AI Engineer to architect, prototype, and ship multimodal data processing systems for Government and Military clients, owning the lifecycle of AI solutions from research to deployment.
Responsibilities:
- Design and implement production-grade RAG pipelines and agentic workflows using Python
- Evaluate new models (LLMs, embedding models, object detection), prototype approaches for SBIR/government deliverables, and run experiments to prove what actually works
- Partner with the team to document architectures, contribute to technical reports for contract deliverables, and participate in pre-sales calls to architect solutions for complex client needs
Requirements:
- 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
- Experience operating within AWS/GovCloud environments
- Experience fine-tuning NLP or object detection models
- Familiarity with LLM evaluation frameworks (hallucination detection, drift monitoring)
- Knowledge of government security standards and working in different classification environments and on-prem
- Security Clearance: Existing Secret/TS clearance or eligibility is a significant plus