Evaluation Platform & Infra Engineer for AI Research

Bison; San Francisco (CA); On-site; USD 300,000 - 350,000; Full time

Benefits offered by this job

Health, dental, vision benefits

Unlimited PTO

Parental leave

Relocation support

Job summary

Thinking Machines is hiring for a role focused on building a self-serve platform for authoring, running, and analyzing model evaluations across diverse tasks and datasets. You will work with Python, data pipelines, APIs, and frontend tools, collaborating closely with cross-functional teams including pre-training and applied research to improve evaluation processes.

The position emphasizes end-to-end platform development, reproducibility, and a strong engineering foundation in a fast-moving

Qualifications

• Bachelor’s degree or equivalent in CS/engineering/ML or related field.
• Two years of post-grad experience as software/ML engineer.
• Experience building evaluations, benchmarks, graders, or model-quality systems for large models.
• Strong software engineering fundamentals for reliable, maintainable systems.
• Proficiency in Python and Rust; React/TypeScript on the frontend.
• Experience with databases, data pipelines, distributed systems.

Responsibilities

• Design, build, and maintain the evaluation platform for model assessments.
• Work across evaluation libraries, data pipelines, APIs, and user apps end-to-end.
• Create abstractions for evaluation tasks, environments, graders, datasets, and outputs.
• Ensure results are reproducible via versioning, provenance, and quality controls.
• Collaborate with researchers to turn bespoke workflows into self-serve systems.
• Coordinate with Research Tooling and internal platform teams.

Skills

Backend development

Data pipelines

Distributed systems

Research collaboration

Education

Bachelor’s degree or equivalent

Tools

Python

Rust

React

TypeScript

APIs

Databases

Job description

Thinking Machines is hiring for a role focused on building a self-serve platform for authoring, running, and analyzing model evaluations across diverse tasks and datasets. You will work with Python, data pipelines, APIs, and frontend tools, collaborating closely with cross-functional teams including pre-training and applied research to improve evaluation processes.

The position emphasizes end-to-end platform development, reproducibility, and a strong engineering foundation in a fast-moving