Member of Technical Staff, Frontier AI

Responsibilities

• Own research and evaluation initiatives end-to-end, including problem framing, data design, quality calibration, and signal validation.
• Design ML-oriented data systems including task definitions, annotation schemas, rubrics, incentives, and pipelines optimized for downstream model performance.
• Analyze model and system failures to identify root causes, edge cases, and opportunities for improvement.
• Translate ambiguous real-world system behavior into structured evaluation frameworks and new data categories.
• Collaborate closely with researchers and domain experts to calibrate quality early and continuously improve research signal.
• Rapidly iterate on evaluations, datasets, and feedback loops to improve model and system performance.
• Act as a quality gate by blocking claims, pausing work, or recommending scope changes when research signal or data integrity is insufficient.
• Partner with cross-functional and client-facing teams to communicate research progress through clear and evidence-based narratives.
• Identify gaps in data and evaluation coverage and recommend where to invest, iterate, or stop based on research findings and expected impact.
• Work directly with experts during project kickoff, calibration, and iterative research cycles.
• Apply a systems-level perspective to improve end-to-end model and agent performance rather than isolated components.

Skills

Requirements

• Strong judgment regarding research signal quality and the ability to determine when findings are sufficiently robust to be externalized.
• Experience designing ML-oriented datasets, evaluation frameworks, and quality assurance processes.
• Ability to translate messy and ambiguous real-world system behavior into structured research and evaluation opportunities.
• Ability to operate effectively in high-ambiguity environments with strong ownership and decisive judgment.
• Clear written and verbal communication skills, particularly when explaining trade-offs, limitations, data integrity, and signal strength to technical and non-technical stakeholders.
• Proven ability to work directly with domain experts during project kickoff, quality calibration, and iterative development.
• Systems-level mindset focused on improving end-to-end model or agent performance.
• Experience with reinforcement learning environments, simulators, or feedback-driven training systems is preferred.
• Experience improving agentic systems or AI systems operating in real-world workflows is preferred.
• Experience working within applied research or production environments with direct impact on deployed AI systems is preferred.
• Experience designing evaluations for complex or real-world tasks is preferred.
• Familiarity with expert incentive design and expert engagement in high-stakes technical projects is preferred.

Benefits

• Full-time remote position.
• Base salary of $240,000–$350,000 per year.
• Eligibility for equity compensation.
• Potential performance-based bonuses subject to role and company policies.
• Up to 100% reimbursement for health insurance premiums.
• Paid time off.
• 401(k) plan with company match.
• Additional benefits supporting a high-performing remote-first workforce.
• Opportunity to work at the intersection of frontier AI research, data design, evaluation, and deployed AI systems.
• Opportunity to directly influence model and agent performance through rigorous research, evaluation, and iterative development.