Mid-Level Research Engineer, Benchmarks

About the Role

Join a small, technical research and engineering team building rigorous benchmarks for evaluating AI agents on realistic, domain-specific workflows. You will own benchmark design and implementation, helping ensure evaluation results are reliable and useful to research and industry teams.

What You'll Do

• Design, implement, and maintain benchmarks for evaluating AI agents on domain-specific tasks.
• Collaborate with subject-matter experts to turn real workflows into realistic tasks and evaluation criteria.
• Build reliable infrastructure to run models and agents against evaluation tasks at scale.
• Develop metrics and analyses to assess benchmark difficulty, reliability, and failure modes.
• Validate how benchmark results relate to real-world performance and evaluation needs.
• Write clear technical documentation and reports for research and engineering audiences.

What We're Looking For

• Two to four years of experience in software engineering, machine learning engineering, or research, including at least two years focused on AI benchmarks, evaluations, or agent environments.
• Hands-on experience designing, implementing, and operating benchmarks or evaluation infrastructure for AI agents or large language models.
• Proficiency with Python, Docker, and Linux environments.
• Experience working with subject-matter experts to model workflows across technical or business domains and define evaluation criteria.
• Experience developing metrics, statistical analyses, or validation studies for benchmark quality and real-world relevance.
• Strong technical writing, attention to detail, and ability to work independently in an early-stage environment.
• Experience with reinforcement learning pipelines, data generation, or agent evaluation is useful. Published work or technical writing on AI evaluation is also valued.

Compensation & Benefits

Annual salary range: $100,000 to $170,000 USD. Visa sponsorship is available.

Location

On-site in Singapore, Singapore.