SW Development Engineer 2

Dexcom; San Diego (CA); Remote; USD 91,000 - 152,000; Full time

Benefits offered by this job

Comprehensive benefits

Growth opportunities

Career development

Tuition reimbursement

Innovative organization

Job summary

Dexcom is seeking an AI Platform Engineer to build and operate scalable model-serving infrastructure on Google Kubernetes Engine (GKE) and develop AI gateways across multiple providers. You will automate access, budgets, and spend alerts, while implementing cost reporting and token accounting across models and providers, with a focus on reliability and efficiency.

You will work with Python, GCP/Kubernetes, CI/CD, and infrastructure-as-code tools like Terraform or Pulumi to optimize cloud unit

Qualifications

• Typically requires a Bachelor’s degree in a technical discipline and 2–5 years of related experience, or a Master’s degree and 0–2 years of equivalent industry experience.
• Experience delivering production software or cloud-platform components.

Responsibilities

• Build and operate scalable model serving on GKE, including vLLM.
• Implement AI gateways with multi-provider integration, cost-aware routing, and reliable fallbacks.
• Automate internal developer access, budgets, usage limits, and spend alerts across models and providers.
• Build usage and cost reporting by developer, team, model, and provider; reconcile token accounting with provider billing.

Skills

Python

GCP

Kubernetes

CI/CD

Terraform

Pulumi

Education

Bachelor’s degree in a technical discipline

Master’s degree (optional)

Tools

LiteLLM

vLLM

Vertex AI

OpenAI

Job description

The Company

Dexcom Corporation (NASDAQ DXCM) is a pioneer and global leader in continuous glucose monitoring (CGM). Dexcom began as a small company with a big dream: To forever change how diabetes is managed. To unlock information and insights that drive better health outcomes. Here we are 25 years later, having pioneered an industry. And we're just getting started. We are broadening our vision beyond diabetes to empower people to take control of health. That means personalized, actionable insights aimed at solving important health challenges. To continue what we've started: Improving human health.
We are driven by thousands of ambitious, passionate people worldwide who are willing to fight like warriors to earn the trust of our customers by listening, serving with integrity, thinking big, and being dependable. We've already changed millions of lives and we're ready to change millions more. Our future ambition is to become a leading consumer health technology company while continuing to develop solutions for serious health conditions. We'll get there by constantly reinventing unique biosensing-technology experiences. Though we've come a long way from our small company days, our dreams are bigger than ever. The opportunity to improve health on a global scale stands before us.

Meet The Team

Release Engineering builds cost-efficient AI platforms for product teams and internal developers. We operate traditional ML and generative AI models at scale on GCP/GKE, automate model delivery, and manage usage across self-hosted and external providers. We partner with ML Engineering on model quality and training, and AI Engineering on application behavior. You will independently deliver platform components and measurable cost and efficiency improvements.

Where You Come In

• You will build and operate scalable model serving on GKE, including vLLM; measure and reduce cost per request and token.
• You will implement AI gateways using tools such as LiteLLM, with multi-provider integration, cost-aware routing, and reliable fallbacks.
• You will automate internal developer access, team budgets, usage limits, and spend alerts across self-hosted models and providers such as Vertex AI and OpenAI.
• You will build usage and cost reporting by developer, team, model, and provider; reconcile token accounting with provider billing and infrastructure spend.
• You will build CI/CD and GitOps automation for model pipelines, registry promotion, validation, deployment, and rollback; manage infrastructure as code.
• You will tune caching, batching, resource allocation, and autoscaling using load tests and telemetry to lower unit cost within model-quality, latency, and reliability targets.
• You will resolve platform incidents with partner teams; improve tests, runbooks, and release reliability.

What Makes You Successful

• You have experience independently delivering production software or cloud-platform components using Python and automated tests.
• You have hands-on GCP/Kubernetes experience operating and right-sizing model-serving or compute workloads.
• You have experience building CI/CD, GitOps, and infrastructure-as-code automation with tools such as Terraform or Pulumi.
• You have experience measuring usage, attributing costs, and improving cloud unit economics; multi-provider gateways such as LiteLLM are preferred.
• You have strong troubleshooting and collaboration skills; vLLM, model registries, or comparable model-delivery experience is preferred.

What You’ll Get

• A front row seat to life changing CGM technology. Learn about our brave #dexcomwarriors community.
• A full and comprehensive benefits program.
• Growth opportunities on a global scale.
• Access to career development through in-house learning programs and/or qualified tuition reimbursement.
• An exciting and innovative, industry-leading organization committed to our employees, customers, and the communities we serve.

Travel Required

• 10%

Education And Experience

• Typically requires a Bachelor’s degree in a technical discipline and 2–5 years of related experience, or a Master’s degree and 0–2 years of equivalent industry experience.

Flex Workplace:

Your primary location will be a home office. You will not have an assigned workstation and will work with your manager to determine office visit needs. You must live within commuting distance of your assigned Dexcom site (typically 75 miles/120km).

Please note: The information contained herein is not intended to be an all-inclusive list of the duties and responsibilities of the job, nor are they intended to be an all-inclusive list of the skills and abilities required to do the job. Management may, at its discretion, assign or reassign duties and responsibilities to this job at any time. The duties and responsibilities in this job description may be subject to change at any time due to reasonable accommodation or other reasons. Reasonable accommodations may be made to enable individuals with disabilities to perform essential functions.

An Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity, age, national origin, or protected veteran status and will not be discriminated against on the basis of disability. Dexcom’s AAP may be viewed upon request by contacting Talent Acquisition at [e-mail].

If you are an individual with a disability and would like to request a reasonable accommodation as part of the employment selection process, please contact Dexcom Talent Acquisition at [e-mail].

AI in Hiring Notice:

We may use AI supported tools to help make our hiring process more efficient, consistent, and accessible for candidates around the world. All hiring decisions are made by people.

Salary

$91,400.00 - $152,300.00 #DexcomUS