Search
Go
Research Engineer – Benchmarks
Summary by AIEngineer.careers
Research Engineer – Benchmarks is a AI Research Engineer role (full-time). with Centre. in SAN FRANCISCO, US. Compensation shown: $100K–$200K. Imported listing (source: careers.centre.edu). Apply on the employer's site (careers.centre.edu).
Imported listing (source: careers.centre.edu) · Apply on careers.centre.edu
SAN FRANCISCO · US
$100K–$200K
Full-time
MID
The sections below reproduce the third-party job description for reference. AIEngineer.careers does not write or control this text.
Imported job description
Sourced from careers.centre.edu
Kadir AI LLC is seeking a Research Engineer to design and develop high-quality benchmarks for evaluating frontier AI agents across realistic, domain-specific tasks. The ideal candidate will leverage Python, Docker, and Linux to build robust evaluation frameworks that measure agent performance accurately. This role contributes to advancing AI safety and capability assessment through rigorous benchmarking methodologies.
Responsibilities
- Design and build high-quality benchmarks for evaluating frontier AI agents
- Develop domain-specific task evaluations for AI capabilities
- Implement evaluation frameworks using Python, Docker, and Linux
Requirements
- Proficiency in Python programming
- Experience with containerization (Docker)
- Strong understanding of Linux environments
- Background in AI/ML evaluation or research preferred
Nice to Have
- Experience with LLM evaluation or AI agent frameworks
- Familiarity with benchmarking methodologies in AI research
- Contributions to open-source AI projects
Tech Stack
C
Centre
City of Troy · US · 1+ employees
Kadir.ai LLC is an AI-native company that provides WorkCentral, a unified HRIS platform for startups and enterprises that integrates multiple business modules such as payroll, ATS, performance tracking, and document AI. Additionally, the company is building a recruiting VMS to streamline the end-to-end technical hiring process.
