SW Development Engineer 1
About The Position
Dexcom’s Release Engineering team builds cost-efficient AI platforms for product teams and internal developers. The team operates traditional machine-learning and generative AI models at scale on GCP and GKE, automates model delivery, and manages usage across self-hosted and external providers. It partners with ML Engineering on model quality and training, and with AI Engineering on application behavior. This role contributes with guidance from experienced engineers. The engineer will help operate models on GKE, including vLLM serving; maintain AI router configurations and provider integrations; support developer access, team budgets, usage limits, and cost reporting; build CI/CD automation for model pipelines; and maintain infrastructure-as-code and GitOps configurations. The role also tracks model token, cache, and resource usage; helps optimize caching, batching, and autoscaling; and troubleshoots serving and pipeline issues while maintaining tests and runbooks. The primary work location is a home office, with no assigned workstation. The employee will work with their manager to determine office visit needs and must live within commuting distance—typically 75 miles/120 km—of their assigned Dexcom site. Travel required: 10%.
Requirements
- Python, Git, and automated testing skills demonstrated through projects, internships, or professional work.
- Foundational knowledge of Linux, containers, Kubernetes, and GCP.
- Understanding of CI/CD, infrastructure as code, and model-delivery workflows.
- Systematic troubleshooting, clear communication, and willingness to learn.
- Typically requires a bachelor's degree in a technical discipline and 0–2 years of related experience.
- Must live within commuting distance of the assigned Dexcom site, typically 75 miles/120 km.
Nice To Haves
- Exposure to Terraform, Pulumi, or equivalent infrastructure-as-code tools.
- Interest in AI usage accounting, cloud cost efficiency, and multi-provider APIs.
- LiteLLM or model-serving exposure.
Responsibilities
- Help operate models on GKE, including vLLM serving, and track cost per request and token at scale.
- Maintain AI router configurations using tools such as LiteLLM for provider integration, routing, and fallbacks.
- Support internal developer access, team budgets, usage limits, and cost reporting across providers such as Vertex AI and OpenAI.
- Build CI/CD automation for model pipelines, registry promotion, testing, deployment, and rollback.
- Maintain infrastructure-as-code and GitOps configurations for repeatable cloud and Kubernetes changes.
- Track per-model tokens, cache hits, and resource usage; help tune caching, batching, and autoscaling to reduce cost within quality and reliability targets.
- Troubleshoot serving and pipeline issues with teammates, and maintain tests and runbooks.
Benefits
- A full and comprehensive benefits program.
- Growth opportunities on a global scale.
- Career development through in-house learning programs and/or qualified tuition reimbursement.
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Entry Level
