AI Engineer- hybrid

Markon•Annapolis Junction, MD

2d•$160,000 - $185,000•Hybrid

About The Position

Markon is seeking an experienced AI Engineer to support an Intelligence Community customer on the Report Authoring and Dissemination program. The role designs, develops, and integrates AI-enabled capabilities into existing enterprise applications to automate mission workflows, streamline reporting processes, and improve operational efficiency. It focuses on using existing large language models rather than developing models from scratch, with emphasis on agentic AI solutions, prompt engineering, and reliable AI integration. The AI Engineer collaborates with software engineers, systems engineers, and mission stakeholders to deliver scalable, production-ready solutions. The work arrangement allows up to three days of telework per week, subject to customer approval. The stated salary range is USD $160,000 to $185,000 per year. The position requires an active TS/SCI clearance with Polygraph.

Requirements

Active TS/SCI clearance with Polygraph.
Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related technical field.
Strong Python development experience, including building and maintaining production-quality applications.
Hands-on experience developing applications using large language models through commercial or self-hosted APIs.
Experience designing agentic AI workflows, including multi-agent orchestration, prompt chaining, and tool integration.
Experience with AI orchestration frameworks such as LangChain, LlamaIndex, or comparable technologies.
Strong prompt engineering skills and experience testing and validating AI-generated outputs.
Experience integrating AI capabilities into existing software architectures using RESTful APIs and microservices.
Experience developing and deploying applications within Amazon Web Services environments.
Strong analytical, problem-solving, and communication skills, with the ability to collaborate across technical teams.

Nice To Haves

Experience developing retrieval-augmented generation pipelines and working with vector databases.
Familiarity with LLM evaluation, monitoring, and observability tools.
Experience performing exploratory data analysis on structured and unstructured datasets.
Familiarity with MLOps and LLMOps practices for deploying, monitoring, and maintaining AI applications.
Experience supporting Intelligence Community applications, reporting workflows, or dissemination processes.
Experience implementing AI-driven workflow automation within enterprise or mission-critical systems.

Responsibilities

Design, develop, test, and deploy AI-enabled applications and agentic workflows to automate complex mission and reporting processes.
Build and integrate multi-agent solutions using large language models, prompt chaining, tool integration, and orchestration frameworks.
Develop production-quality Python code to support AI capabilities within existing enterprise architectures.
Integrate foundation models through APIs, microservices, and cloud-based services.
Design, test, and optimize prompts and agent instructions to improve accuracy, consistency, and reliability.
Develop evaluation and validation processes to assess AI-generated outputs, identify errors, and ensure mission requirements are met.
Collaborate with software developers, systems engineers, and stakeholders to translate operational requirements into AI-driven solutions.
Evaluate emerging AI technologies, frameworks, and tools and recommend practical improvements to existing capabilities.
Provide technical documentation and communicate AI implementation approaches, tradeoffs, and recommendations to stakeholders.