AI/ML Engineer

McLean, VA

Active TS/SCI with Poly Clearance required

@Orchard is retained by a top geospatial technology company supporting important operations missions to U.S. Government customers. Our client is forging the new frontier of spatial intelligence, helping decision makers and operators navigate what’s happening now and shape what’s coming next.  They are a place for problem solvers, changemakers, and go-getters—where people are working together to help our customers see the world differently, and in doing so, be seen differently. Come be part of a mission, not just a job, where you can: Shape your own future, build the next big thing, and change the world.

This position requires an active U.S. Government Security Clearance at the TS/SCI level with required Polygraph.

Responsibilities:

• Develop, implement, and maintain AI/ML-enabled applications with a focus on agent-based workflows, LLM integration, and retrieval-augmented generation capabilities.
• Design and support agent-based application architectures, including orchestration logic, tool use, memory management, and integration with external systems.
• Implement and maintain RAG pipelines, including document processing, embedding generation, retrieval configuration, prompt assembly, and response optimization.
• Integrate LLMs into applications using available APIs, AI frameworks, and emerging protocols such as MCP.
• Develop and maintain REST APIs, particularly Python-based services, to support data retrieval, system integration, agent workflows, and application functionality.
• Support full-stack development of production-ready AI applications, including backend services, user-facing components, and enterprise deployment considerations.
• Process, transform, and organize structured and unstructured data to support AI/ML workflows, model interaction, and application performance.
• Design or refine Postgres schemas and data models to improve data organization, query performance, and application scalability.
• Optimize AI-enabled applications for performance, reliability, usability, and maintainability in enterprise environments.

Minimum Qualifications:

• US citizenship required.
• Active TS/SCI clearance with required Polygraph.
• Bachelor’s degree in computer science or related area of study.
• Senior Labor Category: Minimum 8 years of experience with a Bachelor’s degree; or 7 years of experience with a Master’s degree; or 6 years of experience with a Doctorate.
• Willingness to work onsite full time.
• Proficiency in Python and common data/AI libraries.
• Experience developing AI/ML applications, including LLM-integrated applications, RAG workflows, or similar retrieval-based capabilities.
• Experience with agent-based programming concepts, AI frameworks, and tool-based LLM application development.
• Strong understanding of AI/ML foundational concepts, including transformers, algorithms, LLM behavior, data processing, and model integration patterns.
• Experience designing, developing, or integrating REST APIs to retrieve, process, or exchange data across systems.
• Familiarity with production-ready application development practices, including reliability, maintainability, testing, and deployment considerations.

Preferred Qualifications:

• Experience with MCP or similar protocols for connecting AI agents to tools, data sources, and enterprise systems.
• Experience developing full-stack agent-based applications, including frontend interfaces, backend services, orchestration layers, and enterprise deployment patterns.
• Experience with Python REST API frameworks such as FastAPI or Flask.
• Experience implementing or optimizing LLM memory management approaches, including conversational memory, session state, context management, and retrieval-based memory.
• Experience with agent-based application optimization techniques, including prompt/tool orchestration, latency reduction, context window management, evaluation, observability, and cost/performance tuning.
• Experience working with vector databases, embedding models, semantic search, and retrieval configuration.
• Experience with Docker containers and containerized development environments.
• Experience with AWS or other cloud environments.
• Experience with Postgres, data transformation, structured/unstructured data processing, and schema refinement.

Established in 2010, @Orchard has an exceptional reputation, providing talent acquisition solutions to time-sensitive, talent scarcity issues to deliver better talent management ROI.  Our specialty lies in the critical area of program talent acquisition and resource management, not in one narrow skillset, but across many areas of technical and functional delivery. To learn more about our other exciting opportunities, visit our Jobs Page at www.atorchard.com.