SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Arize AI is a Series C AI observability and evaluation platform backed by $135M+ in funding, serving 150+ enterprises including Booking.com, Uber, Siemens, and PepsiCo. The company helps AI engineers monitor, troubleshoot, and optimize generative AI systems and agents in production.
You'll join the open source team to architect and develop new frameworks, libraries, and APIs that simplify LLM monitoring, evaluation, and improvement. This is a high-impact individual contributor role with significant autonomy and visibility.
Key responsibilities include:
- Design and open-source new observability frameworks, pipelines, and APIs for LLM evaluation
- Collaborate with the broader AI open source ecosystem, review contributions, and guide project direction based on developer feedback
- Prototype and iterate on state-of-the-art LLM techniques, translating research into practical tooling
- Integrate with the Arize platform to surface deeper insights on LLM behavior, helping teams diagnose issues like hallucinations and bias
- Create educational content (blog posts, white papers, tutorials, documentation) to grow the LLM evaluation community
You're an engineer who is passionate about AI and open source development. You thrive in fast-paced environments, solve ambiguous problems creatively, and are driven by empirical results. You have hands-on experience with LLM frameworks and prompt engineering, strong TypeScript proficiency (including isomorphic code for clients, servers, and edge runtimes), and a track record of open source contributions or public AI projects. Familiarity with ML observability tools and debugging AI applications is a plus.
The role offers the opportunity to shape how developers measure and understand AI performance at scale, with your work used by engineers worldwide. You'll have high ownership, autonomy, and the ability to drive major initiatives from day one.
