ABOUT BASETEN
Baseten powers mission-critical inference for the world's most dynamic AI companies, like Cursor, Notion, OpenEvidence, Abridge, Clay, Gamma, and Writer. By uniting applied AI research, flexible infrastructure, and seamless developer tooling, we enable companies operating at the frontier of AI to bring cutting-edge models into production. We're growing quickly and recently raised our $1.5B Series F, led by Altimeter Capital, Conviction Partners, and Spark Capital. Join us and help build the platform engineers turn to ship AI products.
THE ROLE
Baseten is seeking talented and experienced Software Engineers to join our Platform team within the Infrastructure organization. As a member of Baseten's Platform Team, you will own the systems that let every engineer at Baseten prove their code works before it reaches production. Our product runs mission-critical AI inference for customers who measure downtime in dollars per second, which means our internal bar for correctness, performance, and failure tolerance has to be exceptional.
Your focus is the full testing stack: fast and reliable unit test tooling, integration harnesses that spin up realistic environments on demand, load and performance testing for GPU-backed inference workloads, and resilience testing that deliberately breaks things so our customers never have to find out what happens when a node dies mid-request. This is a builder role with org-wide leverage. You won't be writing tests for other teams — you'll be building the frameworks, harnesses, and feedback loops that make writing good tests the path of least resistance, and you'll set the standards for what "well-tested" means at Baseten.
RESPONSIBILITIES
Own Baseten's testing strategy end to end — define the standards, the tiers, and the tooling that engineering teams build against.
Build and maintain unit, integration, load and performance testing frameworks
Design end to end test infrastructure that provisions realistic dependencies on demand — ephemeral Kubernetes namespaces, containerized service dependencies, etc.
Build resilience and chaos testing capabilities: fault injection, network partition and latency simulation, pod and node failure scenarios, dependency degradation, and automated verification that our systems degrade gracefully and recover.
Attack test suite reliability head-on — flake detection and quarantine, test impact analysis and selective execution, parallelization, and aggressive reduction of end-to-end CI wall time.
Build observability into the testing layer itself: coverage reporting, test health dashboards, failure triage tooling, and clear signals about which areas of the codebase are under-tested.
Create project templates and shared libraries so new services start with a complete testing setup on day one.
Partner directly with product and infrastructure teams — embed where needed, understand their hardest testing problems, and turn one-off solutions into platform capabilities.
Mentor engineers across the org on testing practice and raise the collective bar through code review, documentation, and internal advocacy.
REQUIREMENTS
Strong proficiency in Go and/or Python, with hands-on experience building test tooling and libraries used by other engineers.
Deep experience with testing frameworks and their internals — pytest, Go's testing package, testify, testcontainers, or equivalents — including the ability to extend them, not just use them.
Experience designing integration test infrastructure for distributed systems, including ephemeral environment provisioning and dependency management.
Practical experience with load and performance testing tools (k6, Locust, Vegeta, JMeter, Gatling, or similar) and the judgment to interpret results and drive action from them.
Solid Kubernetes and Docker fundamentals — you can build test infrastructure that runs on and tests against real cluster environments.
Advanced understanding of CI/CD, including how to keep large test suites fast, deterministic, and trustworthy at scale.
A track record of measurably improving testing culture on an engineering team — you have opinions on what to test, what not to test, and where the ROI actually is.
Are excited about building foundational infrastructure and are comfortable working independently on ambiguous, high-impact technical challenges
BENEFITS
Competitive compensation, including meaningful equity
(U.S. only) 100% coverage of medical, dental, and vision insurance for employee and dependents
Flexible PTO policy including company wide Winter Break (our offices are closed from Christmas Eve to New Year's Day!)
Paid parental leave
Fertility and family-building stipend through Carrot
(U.S. only) Company-facilitated 401(k)
Exposure to a variety of ML startups, offering unparalleled learning and networking opportunities.
Apply now to embark on a rewarding journey in shaping the future of AI! If you are a motivated individual with a passion for machine learning and a desire to be part of a collaborative and forward-thinking team, we would love to hear from you.
At Baseten, we are committed to fostering a diverse and inclusive workplace. We provide equal employment opportunities to all employees and applicants without regard to race, color, religion, gender, sexual orientation, gender identity or expression, national origin, age, genetic information, disability, or veteran status.
We are an Equal Opportunity Employer and will consider qualified applicants with criminal histories in a manner consistent with applicable law (by example, the requirements of the San Francisco Fair Chance Ordinance, where applicable).
Skills Required
- Strong proficiency in Go and/or Python
- Hands-on experience building test tooling and libraries used by other engineers
- Deep experience with testing frameworks and their internals, such as pytest, Go's testing package, testify, or testcontainers
- Experience designing integration test infrastructure for distributed systems
- Experience with ephemeral environment provisioning and dependency management
- Practical experience with load and performance testing tools such as k6, Locust, Vegeta, JMeter, or Gatling
- Solid Kubernetes and Docker fundamentals
- Advanced understanding of CI/CD and large-scale test suite optimization
- Track record of measurably improving testing culture on an engineering team
- Ability to build foundational infrastructure independently in ambiguous, high-impact technical environments
Baseten Compensation & Benefits Highlights
The following summarizes recurring compensation and benefits themes identified from responses generated by popular LLMs to common candidate questions about Baseten and has not been reviewed or approved by Baseten.
-
Fair & Transparent Compensation — Feedback suggests pay targets the top of market with explicit ranges in postings and a stated aim to provide 90th percentile salaries with equity. Role descriptions emphasize competitive, experience-based pay bands and meaningful stock grants.
-
Healthcare Strength — Healthcare is described as fully covered for medical, dental, and vision for employees and their families, reducing out-of-pocket costs. This comprehensive coverage is consistently highlighted alongside other core benefits.
-
Leave & Time Off Breadth — Time off policies include unlimited PTO with a minimum expectation of at least four weeks, 16 paid company holidays, and a company-wide winter break. These elements indicate substantial protected time away from work.
Baseten Insights
What We Do
AI’s future won’t be a few massive models built by a handful of labs. It’ll be millions of specialized models embedded into every product, workflow, and experience by the people closest to the customer. The foundation of that future is inference. Inference determines the performance, reliability, latency, and economics of every AI product. For AI to scale globally, it must be as reliable, fast, cost-effective, and high-quality as possible. That’s why Baseten exists. Companies like Abridge, Cursor, Lovable, Notion, and OpenEvidence depend on Baseten to power mission-critical AI workloads in production.
Why Work With Us
We’re an interdisciplinary team of researchers, engineers, and operators building the Inference Cloud our AI future demands. We’re running at a hard systems problem that requires first-principles thinking across the entire stack. The bar is high. We work hard, move fast, and care deeply about quality.








