The RoleWe'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
Compensation: $230,000 - $300,000
We are committed to offering a comprehensive and competitive total rewards package, including robust health benefits, commuter benefits, and meaningful ownership opportunities through equity. Compensation decisions are made holistically, ensuring fairness and alignment with market benchmarks while recognizing individual contributions and potential.
Benefits offered include:- 401(k) Retirement Savings Plan
- Equity Compensation
- Dinner Provided via DoorDash & stocked kitchen for NY employees
- Medical, Dental, and Vision coverage coverage of up to 100% premiums for you and your family
- HSA / FSA
- 11 paid holidays each year
- Unlimited PTO
- Training and professional development
- Hybrid Work Schedule (4 days onsite, 3 if located > 1 hour away)
