LLM Model Deployment Engineer

An active TS//SCI clearance with polygraph is required for this role

Bitwise is a leading provider of mission-focused intelligence solutions that advance national security for the Intelligence Community and Department of Defense. We're a small and growing company, so you can expect to hop in on the ground floor with us and be a consequential member of the team. You'll be more than a contract performer for us — you'll also be asked for ideas to improve our company and improve your career, and you'll contribute to our team culture.

We value growth and community above almost all else, so we gather regularly for game nights, happy hours, tech talks, and plenty more. We think you'll like it here!

Remember, Bitwise is not a cult.

Bitwise hires talented engineers who are driven by purpose and who value a culture of technical excellence, growth, and overall wellness. We deliver new and innovative intelligence solutions to our customers at the very forefront of our country's national security missions. And we do it every single day. Our work matters, and so will you.

We ask that every new hire be able to:

• Contribute meaningful thought leadership — if not right away, over time
• Interact with our customers and earn their confidence in your abilities
• Be detailed, even if that means taking a little more time to get it right
• Contribute their ideas and ideals to improve all aspects of our company
• Allow us to invest in their education so we both grow together

We're building the next generation of AI infrastructure that will power innovation across our customer's organization, and we need a software engineer to help us do it. In this role, you'll support our AI infrastructure team by helping build and maintain the foundation for customer AI capabilities while supporting a broader ecosystem of AI-enabled applications. Your focus will be ensuring access to the highest available quality LLMs to users throughout the inference software stack.

Requirements shift quickly as mission needs evolve and new technologies emerge, so you'll keep sharpening your skills and learning to turn loosely defined problems into working solutions. You'll work directly with our team to develop robust systems that power critical national security capabilities.

What You'll Do:

• Procure, configure, and test new inference models, preparing them for release to our user base
• Develop in-house services and techniques to guarantee continual high-quality inference service for our customer
• Work with model vendor teams and representatives to create reliable pipelines for closed‑source model usage
• Collaborate with teammates on surge efforts to support short‑term, high-priority inference needs from our customer
• Engage with other teams in our organization to establish solid infrastructure for our services and integrate LLM‑powered tools for user needs

• 3 years of experience in software engineering, OR a B.S. in a technical discipline plus 4 additional years of related experience
• Experience with Python and/or other modern programming languages
• Familiarity with Argo CD and/or other CI/CD frameworks
• Experience with Kubernetes/Helm
• Familiarity with AWS or other cloud service providers
• Ability to learn new technologies quickly
• Strong communication skills and willingness to ask questions
• Experience with vLLM, LiteLLM, or similar inference-serving frameworks
• Experience with other LLM hosting frameworks and practices
• Experience supporting production software using Site Reliability Engineering (SRE) best practices
• Experience with Elastic, Grafana/Prometheus, or other observability frameworks and practices
• Experience with Docker and containerization
• Experience in traffic shaping and quality‑of‑service engineering
• Knowledge of and interest in hosting AI…