Brellium logo
Brellium

Senior Platform Engineer

New York City, USAHybridPosted 1 week ago

Apply opens Brellium's site. When you're back, we'll ask whether you applied.

Job type
Full-time
Work mode
Hybrid
Level
Senior
Department
Engineering
Experience
5+ years experience
Posted
Sep 23, 2026

About the role

The Role

We're hiring a founding platform engineer. Brellium audits clinical notes against millions of criteria a day, with AI pipelines processing billions of tokens. You'll be the first person whose full-time job is scaling towards a highly available production environment by making our infrastructure reliable and observable, defining the patterns others build on, and making every engineer more effective in their work.

This is a hands-on senior IC role reporting directly to the VP of Engineering. You'll set this function's roadmap in collaboration with engineering leadership.

What You'll Do

  • Manage and scale infrastructure that runs audits on clinical notes across millions of criteria daily
  • Define and support infrastructure patterns that can improve latency (e.g. making audits real time), reliability, and cost effectiveness
  • Improve developer productivity through CI/CD and local / testing environments
  • Simplify observability and drive key reliability metrics across all of our services, including AI pipelines that process billions of tokens daily
  • Manage our infrastructure and developer tooling spend
  • Steward our security posture (e.g. SOC 2, HIPAA compliance)
  • Consolidate SSO, identity, device management, and access controls across internal tools

You Might Be a Fit If

  • You have owned the infrastructure / platform function somewhere
  • You have informed opinions about infrastructure and collaborate with product engineers to find right-sized solutions
  • You understand product engineering work to a high degree
  • You measure your work by whether other engineers actually use it
  • You'd rather ship something narrow in two weeks than complete in two months
  • You are used to the blurred lines at a startup and are biased towards taking ownership
  • You are experienced working in an environment with a high degree of autonomy

Required Skills

  • 5+ years where platform was your primary work
  • Built production infrastructure at an early-stage startup
  • Depth in AWS and infrastructure-as-code. Our tech stack includes AWS, Vercel, Azure Foundry, Claude Platform, OpenAI Platform, Gemini, and Clickhouse
  • You know how to write production-level code. Our applications are written in Python and Typescript
  • You have driven towards a target number for a cloud bill
  • You have managed audits for software compliance (e.g. SOC 2)

Nice to Have

  • Healthcare or another regulated industry that includes sensitive-data handling
  • Experience with LLM infrastructure: inference cost management, gateways (e.g. Bifrost), tracing and evals (e.g. Langfuse)
  • Rolled out an identity provider like Okta
  • Mentored engineers or led a small team