Python Generative AI Engineer

## About the role Looking for PURPOSE? At GovStar, we found it. We love the work we do, the people we do it with, and the impact we have. We're looking for talented technologists and creatives with the character, courage, and commitment to achieve greatness and grow together. We're a tight group of individuals coming together to produce Legendary Teams. We are using technology and creativity to unlock the future of government and shape a brighter future for the country we love. Discover us @ www.govstar.us GovStar is seeking a Python Generative AI Engineer with strong hands-on coding skills and personal drive to support emerging Generative AI initiatives for national security customers. Ideal candidates will have proven experience building LLM-powered applications, RAG pipelines, and agentic architectures. ## Responsibilities Responsibilities include, but are not limited to: - Design, develop, and maintain Generative AI applications, including RAG pipelines, agentic workflows, and LLM-powered tools. - Architect and implement robust backend services and APIs that integrate with large language models and vector databases. - Build and optimize retrieval-augmented generation systems, including document ingestion, chunking strategies, embedding pipelines, and retrieval orchestration. - Design and implement agentic structures using frameworks. - Develop and refine prompt engineering strategies to maximize LLM output quality and reliability. - Ensure the performance, quality, and responsiveness of applications. - Conduct code reviews and maintain code quality standards. - Stay current on the latest advancements in Generative AI technologies, tools, and best practices. ## Minimum Requirements - US citizenship and ability to obtain DHS Public Trust clearance - BS in Computer Science or related field - At least 12 years of relevant experience in software engineering, with demonstrated experience building Generative AI or LLM-powered applications - Active LinkedIn profile, linked in resume or application - Publicly available GitHub or portfolio demonstrating relevant Python work (please include link in resume!) - Profile picture included in application - Strong Python experience and skills - Hands-on experience with RAG architectures, vector databases, and LLM orchestration frameworks - Strong individual contributor with continuous, hands-on coding experience, spending approximately 80% of their time writing code - Strong ability to analyze technically complex problems and develop and implement new and innovative solutions - Must be located in the United States, in Eastern or Central Time Zones. ## Preferred Requirements - Full stack development experience, including proficiency in frontend development with React, TypeScript, and CSS alongside Python backend development - Experience with LLM orchestration frameworks - Experience with vector databases - Strong experience with prompt engineering techniques - Working knowledge of Azure cloud services - Experience developing within VSCode and working with GitLab for source control and CI/CD pipelines - Ability to develop and work with APIs, including RESTful services, authentication methods, and data formats - Comprehensive understanding of SQL/PostgreSQL and NoSQL databases, including integration within the same application when appropriate - Experience with Docker - Experience developing with additional languages including JavaScript, TypeScript, React, YAML, and JSON - Ability to work independently on complex tasks with little direction - Based in the DMV (D.C, Maryland, Virginia) Area ## Relevant Technologies - Core Stack – Python, OpenAI Agents, Vector Databases, LLM APIs, LiteLLM - Full Stack – React, CSS, TypeScript - Database – SQL, PostgreSQL, CosmosDB - Cloud – Azure (Azure OpenAI, Azure AI Search) - Version Control – Git, GitHub/GitLab - Project Management – Jira, Confluence ## What we offer This is a full-time, salaried position. Benefits include: - Health/Dental/Vision insurance - 401(k) matching - Paid time off - Employee shares program