Research Engineer, Benchmarks

About the Role

This role sits at the heart of a small, technical team building high-quality benchmarks to evaluate frontier AI agents on realistic, domain-specific workflows. You will own the design and implementation of evaluations that frontier labs and enterprise customers rely on to understand real-world agent performance. The work is critical to ensuring benchmarks are rigorous, credible, and practically meaningful.

What You'll Do

• Design, implement, and own the quality of internal benchmarks for evaluating frontier agents on domain-specific tasks.

• Partner with subject-matter experts to define realistic workflows and translate them into evaluation criteria.

• Build reliable infrastructure to run models and agents against benchmark tasks at scale using Python, Docker, and Linux environments.

• Develop metrics and statistical analyses to measure benchmark difficulty, reliability, and failure modes.

• Validate that benchmark performance correlates with real-world evaluations and customer needs.

• Write clear technical documentation and benchmark reports for research and engineering audiences.

What We're Looking For

• 2 to 4 years of experience in research engineering or machine learning engineering, with a focus on AI benchmarks, evaluation infrastructure, or agent environments.

• Strong proficiency in Python, Docker, and Linux for building research or production infrastructure.

• Demonstrated experience designing and running benchmarks or evaluation environments for AI agents or large language models.

• Experience developing metrics, statistical analyses, or validation studies to assess benchmark quality and real-world correlation.

• Experience collaborating with domain experts to translate workflows into structured evaluation tasks.

• Strong technical writing skills, with published papers or technical posts on AI benchmarking, model evaluation, or failure modes being a plus.

• Ability to reason from first principles about task design, scoring, and edge cases.

• Comfort working independently in fast-paced, early-stage startup environments with unstructured problem spaces.

• Experience with reinforcement learning training pipelines, data generation, or RL agent evaluation is a bonus.

Compensation & Benefits

Salary range: $150,000 to $250,000 USD annually. Visa sponsorship is available.

Location

On-site in Singapore. This is a full-time, in-person role.