Software Engineer I - Inference

DUTIES As a successful candidate for the Software Engineer I - Inference role, you will join our AI infrastructure team to build and maintain the foundation for customer AI capabilities while supporting a broader ecosystem of AI-enabled applications. Your primary focus will be ensuring seamless access to the highest quality large language models (LLMs) throughout the inference software stack. Operating in a dynamic environment where requirements shift as mission needs evolve and new technologies emerge, you will continuously sharpen your skills and turn loosely defined problems into impactful, working solutions.

• Procure, configure, and test new inference models to prepare them for seamless release to the user base
• Develop in-house services and techniques to guarantee continuous, high-quality inference performance
• Partner with model vendor teams to establish reliable integration pipelines for closed-source models
• Collaborate with teammates on surge efforts to address high-priority, short-term customer inference demands
• Engage with cross-functional teams to build resilient service infrastructure and integrate LLM-powered tools for end-user needs

QUALIFICATIONS Three (3) years’ experience as a SWE in programs and contracts of similar scope, type, and complexity is required. A Bachelor’s degree in Computer Science or a related discipline from an accredited college or university is required. Four (4) years of additional SWE experience on projects with similar software processes may be substituted for a bachelor’s degree.

Additional Requirements:

• Develop with Python and other modern programming languages
• Utilize Argo CD or other modern CI/CD frameworks
• Deploy and manage containerized applications using Kubernetes and Helm
• Operate within AWS or other major cloud service provider environments
• Demonstrate a proven ability to rapidly learn and adopt emerging technologies
• Communicate clearly and collaborate proactively to address technical and mission needs

Desired Skills

NICE-TO-HAVES

• Leverage vLLM, LiteLLM, or similar inference-serving frameworks
• Apply modern LLM hosting frameworks and deployment practices
• Support production software using Site Reliability Engineering (SRE) best practices
• Utilize Elastic, Grafana, Prometheus, or other observability frameworks
• Package and manage applications using Docker and containerization
• Implement traffic shaping and quality-of-service engineering strategies
• Demonstrate strong interest and foundational knowledge in hosting AI capabilities