Full performance AI/ML Engineer

Markon is hiring a Full Performance AI/ML Engineer to support an Intelligence Community client in McLean, Virginia. The role designs, develops, integrates, and maintains production-ready AI/ML applications, with a focus on LLM integration, agent-based workflows, and retrieval-augmented generation. It also spans application development, data engineering, and system integration.

Responsibilities:

• Design, develop, implement, and maintain AI/ML-enabled applications, emphasizing LLM integration, agent-based workflows, and RAG capabilities
• Develop and support agentic AI architectures, including orchestration logic, tool integration, memory management, context handling, and connections to external systems
• Design, implement, and optimize RAG pipelines, including document processing, embedding generation, semantic retrieval, prompt assembly, and response optimization
• Develop and maintain Python-based services, REST APIs, backend components, and user-facing application features supporting enterprise AI solutions
• Integrate AI/ML applications with enterprise tools, databases, and structured or unstructured data sources
• Process, organize, and transform data to support AI model integration, retrieval workflows, and application functionality
• Develop and optimize PostgreSQL database schemas, queries, indexing strategies, and data workflows
• Evaluate and benchmark AI/ML application and model performance using appropriate testing and evaluation methodologies
• Optimize AI applications for reliability, latency, performance, usability, maintainability, and scalability
• Apply software engineering best practices throughout the application development lifecycle, including testing, deployment, troubleshooting, and ongoing sustainment
• Collaborate with technical stakeholders and development teams to translate mission requirements into functional, production-ready AI/ML capabilities