It’s an AI safety and security company.

Job Summary

The ML Researcher plays a pivotal role in advancing AI innovation by conducting deep, end-to-end research focused on emerging AI directions. This role involves designing novel AI benchmarks and creating high-quality evaluation datasets that align with cutting-edge research and organizational priorities. The ML Researcher bridges theoretical AI research and practical application by translating insights from the latest AI literature into actionable benchmarks and evaluation frameworks, particularly in agent frameworks, machine learning models, and emerging AI paradigms.

Responsibilities

• Continuously track and review the latest AI research, conferences, and publications to identify gaps and opportunities in existing benchmarks.
• Propose and design novel, scalable AI benchmarks and evaluation datasets that assess AI systems across coding and non-coding domains.
• Define meaningful evaluation metrics that provide actionable insights into AI model performance.
• Produce clear, comprehensive documentation for each benchmark or dataset, including problem statements, design overviews, evaluation metrics, and testing guidelines.
• Collaborate closely with ML leads, machine learning engineers, project managers, and other stakeholders to align research outputs with organizational goals and industry standards.
• Iterate and refine benchmarks and datasets based on feedback, new research, and emerging use cases.
• Engage actively with the AI research community through conferences, discussions, and continuous learning.

Qualifications

• Deep expertise in AI and machine learning domains, including agent frameworks, deep learning, natural language processing (NLP), computer vision, and emerging AI systems.
• Proven experience in designing benchmarks and evaluation datasets from inception to deployment.
• Strong research and analytical skills with the ability to synthesize academic and industry findings into practical solutions.
• Excellent documentation and communication skills to produce clear, actionable research deliverables.
• Ability to work independently while effectively collaborating with cross-functional teams.
• Educational background in computer science, machine learning, artificial intelligence, or related fields (Bachelor’s degree or higher preferred).

Preferred Skills

• Experience with reinforcement learning environments and managed AI workforce platforms.
• Familiarity with scalable operations automation platforms and hybrid evaluation suites.
• Knowledge of industry-leading AI labs and frontier AI research trends.
• Ability to propose enhancements to evaluation methodologies, including new metrics or benchmark variations.

Experience

• Demonstrated experience conducting comprehensive AI research and designing evaluation frameworks.
• Experience working in fast-paced, innovative AI research environments or organizations.
• Proven track record of delivering high-impact research outputs and collaborating across technical teams.