Open Source AI Engineer - TypeScript for LLM Observability

Arize AI; San Francisco (CA); On-site; USD 185,000 - 200,000; Full time

Benefits offered by this job

Medical, dental, and vision benefits

401(k) plan

Unlimited PTO

Parental leave

Job summary

Arize AI is seeking an Open Source AI Engineer to lead the development of new frameworks, metrics, and tooling for monitoring and improving LLM performance in production. You’ll shape how developers measure AI outputs and contribute to a growing OSS team.

The role emphasizes open-source collaboration, rapid prototyping, and building tooling that scales to real-world AI systems, with a remote-first approach and opportunities to work from NYC or SF offices if desired.

Qualifications

• Hands-on experience with popular LLM frameworks, prompt engineering techniques, and agent harnesses.
• Strong TypeScript proficiency; ability to write isomorphic code across clients, servers, and edge runtimes.
• Open source contributions or active engagement in developer communities.

Responsibilities

• Build LLM Observability Frameworks: design and open-source libraries, pipelines, and APIs to monitor and improve LLM output.
• Collaborate with the community: review PRs and steer project direction to meet developer needs.
• Prototype and iterate rapidly: experiment with cutting-edge LLM techniques for practical tooling.
• Improve observability and debugging: surface deeper insights on LLM behavior and diagnose issues like hallucinations or bias.
• Educate and evangelize: write blogs, tutorials, and docs to grow the LLM eval community.

Skills

Hands-on LLM Experience

Strong TypeScript

Open Source Track Record

ML Observability & Tools

Job description

Arize AI is seeking an Open Source AI Engineer to lead the development of new frameworks, metrics, and tooling for monitoring and improving LLM performance in production. You’ll shape how developers measure AI outputs and contribute to a growing OSS team.

The role emphasizes open-source collaboration, rapid prototyping, and building tooling that scales to real-world AI systems, with a remote-first approach and opportunities to work from NYC or SF offices if desired.