Member of Technical Staff, Realm Lab (frontier AI research)

Compensation context

Listed annual salary range: $600,000–$2,000,000/year. The employer’s base salary is stated separately in the Compensation & Benefits Notice below; these figures differ and should not be treated as the same pay guarantee.

Role: Realm Lab Member of Technical Staff (frontier AI research)

Type of job: full time

Location: Remote

About the role

Realm Lab is adding an MTS (Member of Technical Staff) who will lead research into how frontier AI systems are evaluated and made better.

The job is hands-on and technical, combining ML, evaluation engineering, and data research. Alongside researchers and subject experts, you'll create benchmarks, RL environments, and strong datasets that push model capability and performance forward.

What You'll Do

• Run research and evaluation projects from start to finish: designing tasks, building datasets, validating benchmarks, and analyzing performance.
• Build and check benchmark suites, RL environments, and capability evals for agent workflows, computer use, and new model abilities.
• Produce strong datasets, task specs, grading rubrics, and methods that raise post-training data quality and improve how models are assessed.
• Study model behavior by analyzing failures, building error taxonomies, and finding capability gaps, so the findings steer research.
• Work with researchers and subject experts to plan experiments, tune evaluation quality, and lift model performance.
• Create repeatable eval pipelines and feedback loops that support model development in iterations.
• Add to benchmarks, papers, technical reports, and open research outputs.

What We're Looking For

• A solid technical grounding in CS, ML, AI, or a nearby discipline.
• Practical work designing ML evals, benchmark suites, research datasets, or experiment frameworks.
• Skill in Python, plus experience creating data pipelines, eval tooling, or infrastructure for ML research.
• Knowledge of LLMs, foundation models, post-training methods, and ways of evaluating them.
• Can break real workflows that are complicated into measurable criteria, structured tasks, and research experiments.
• Sharp analytical skill in diagnosing model failures, designing experiments, and judging evaluation quality.
• Comfortable working alone and teaming well with researchers, engineers, and subject experts.

Preferred Qualifications

• Background with RL environments, reward models, simulators, or training systems driven by feedback.
• Experience testing agents that use computers or tools, browser automation, or agent workflows with many steps.
• Knowledge of multimodal reasoning, long-context evals, instruction following, or deep-research benchmarks.
• Background with human-in-the-loop evals, datasets created by experts, or post-training data.
• Published AI research, open-source benchmarks, or evaluation frameworks you've contributed to.

Compensation & Benefits Notice

Nationally, base pay for this full-time job runs $240,000–$350,000. Every employee can receive equity, and bonuses tied to performance may also apply depending on the role and company policy. Benefits cover health-insurance premiums (reimbursed at up to 100%), paid time off, a 401(k) with a company match, and other perks meant for a remote-first team that performs at a high level.

micro1 hires on an equal-opportunity basis. Every qualified applicant is considered without regard to age, color, disability, national origin, race, religion, sex (pregnancy, gender identity, and sexual orientation included), veteran status, genetic information, or any other trait that applicable local laws, ordinances, or regulations protect. Applicants who need help or a reasonable accommodation while applying can ask for it.

AI tools help screen and assess candidates in the hiring process. They are meant to support people's hiring decisions, not to take them over.

Disclaimer

This posting (including duties, qualifications, pay, and benefits) is for information only and is not a binding job offer. micro1 may change, update, or withdraw any part of it at any time and at its own discretion without notice. All hiring decisions follow applicable laws and regulations.

Application process

Submit your application through NorthStar. Employer screening may follow after submission.