About the Role
• Implement and maintain RAG pipelines, including document processing, embedding generation, retrieval configuration, and prompt assembly.
• Integrate LLMs into applications using available APIs and frameworks.
• Develop and maintain REST API interactions to support data retrieval and system integration.
• Design or refine Postgres schemas to improve data organization and query performance.
Minimum Requirements
• Demonstrated ability to conduct independent technical research, evaluate emerging AI/ML approaches, and apply advanced analytical problem-solving comparable to PhD-level research environments.
• Ability to rapidly learn and apply new AI/ML methodologies, tools, and frameworks in support of evolving mission requirements.
• Experience developing AI/ML applications focused on Retrieval-Augmented Generation (RAG), semantic retrieval, LLM integration, or related AI workflows.
• Strong proficiency in Python and modern AI/ML libraries, frameworks, and API integrations.
• Active/current TS/SCI with required polygraph.
• Willingness to work onsite full time.
• US citizenship required.
• Senior Labor Category: Minimum 8 years of experience with a Bachelor’s degree; or 7 years of experience with a Masters degree; or 6 years of experience with a Doctorate
Desired Skills
• Advanced research experience in machine learning, deep learning, natural language processing, generative AI, reinforcement learning, computer vision, or related disciplines.
• Experience publishing research, contributing to open-source AI/ML initiatives, or leading experimental and prototype development efforts.
• Familiarity with model evaluation frameworks, fine-tuning workflows, inference optimization, and AI observability/monitoring tools.
• Experience with vector databases, AWS/cloud environments, Docker, and containerized AI/ML development workflows.
• Experience designing and integrating REST APIs and scalable data architectures.