Your work will span the full lifecycle of model development. You'll research and build new long-horizon evaluations that test the boundaries of what our models can achieve, develop novel approaches to measuring emerging capabilities, and deepen our understanding of how those capabilities develop , both during production RL training and after. You'll also take a cross-organisational view, working across Reinforcement Learning, Pretraining, Inference, Product, Alignment, Safeguards, and other teams to map the landscape of model evaluations at Anthropic and identify critical gaps in coverage.

This role carries significant visibility and impact. You'll help shape the evaluation narrative for model releases, contributing directly to how Anthropic communicates about its models to both internal and external audiences. Done well, you will change how the industry measures and understands model capabilities, significantly furthering our safety mission.

Responsibilities:

• Build new novel and long-horizon evaluations
• Develop novel measurement approaches for understanding how model capabilities emerge and evolve during RL training
• Lead strategic evaluation coverage across the company
• Shape the evaluation narrative for model releases
• Lead and mentor a small team of researchers and research engineers, setting research direction and fostering a culture of rigorous, creative research
• Design evaluation frameworks that balance scientific rigor with the practical demands of production training schedules
• Build and maintain relationships across Anthropic's research organisation to ensure evaluation insights inform training and deployment decisions
• Contribute to the broader research community through publications, open-source contributions, or external engagement on evaluation best practices

You may be a good fit if you:

• Have significant experience designing and running evaluations for large language models or similar complex ML systems
• Have led technical projects or teams, either formally or through sustained ownership of critical research directions
• Are equally comfortable designing experiments and writing code,you can move between research and implementation fluidly
• Think strategically about what to measure and why, not just how to measure it
• Can synthesise information across multiple teams and workstreams to form a coherent picture of model capabilities
• Communicate complex technical findings clearly to both technical and non-technical audiences
• Are results-oriented and thrive in fast-paced environments where priorities shift based on research findings
• Care deeply about AI safety and want your work to directly influence how capable AI systems are developed and deployed

Strong candidates may also have:

• Experience building evaluations for long-horizon or agentic tasks
• Deep familiarity with Reinforcement Learning training dynamics and how model behaviour changes during training
• Published research in machine learning evaluation, benchmarking, or related areas
• Experience with safety evaluation frameworks and red teaming methodologies
• Background in psychometrics, experimental psychology, or other measurement-focused disciplines
• A track record of communicating evaluation results to inform high-stakes decisions about model development or deployment
• Experience managing or mentoring researchers and engineers

Representative projects:

• Designing and implementing a suite of long-horizon evaluations that test model capabilities on tasks requiring sustained reasoning, planning, and tool use over extended interactions
• Building systems to track capability development across RL training checkpoints, surfacing insights about when and how specific capabilities emerge
• Conducting a cross-org audit of evaluation coverage, identifying blind spots, and prioritising new evaluations to fill critical gaps across Pretraining, RL, Inference, and Product
• Developing the evaluation methodology and narrative for a major model release, working with research leads and communications to clearly characterise model capabilities and limitations
• Researching and prototyping novel evaluation approaches for capabilities that are difficult to measure with existing benchmarks
• Leading a team effort to build reusable evaluation infrastructure that serves multiple teams across the research organisation

The annual compensation range for this role is $850,000.

XML job scraping automation by YubHub

We work on the bleeding edge and leverage the most powerful pretrained models and algorithms, making it critical that we ensure our AI systems behave safely and align with organisational values.

You will be responsible for designing novel safety evaluation frameworks, curating high-quality data for robust evaluations and training, prototyping new safety capabilities, and developing safety-focused fine-tuning algorithms.

We’re looking for outstanding individuals with deep expertise in AI safety who can translate research insights into practical solutions while being a strong communicator and collaborative teammate.

The ideal candidate takes the initiative in exploring new safety methodologies and enjoys building world-class, trustworthy AI experiences in a fast-paced applied research environment.

Microsoft’s mission is to empower every person and every organisation on the planet to achieve more.

As employees we come together with a growth mindset, innovate to empower others, and collaborate to realise our shared goals.

Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Starting January 26, 2026, MAI employees are expected to work from a designated Microsoft office at least four days a week if they live within 50 miles (U.S.) or 25 miles (non-U.S., country-specific) of that location.

This expectation is subject to local law and may vary by jurisdiction.

XML job scraping automation by YubHub

We work on the bleeding edge and leverage the most powerful pretrained models and algorithms, making it critical that we ensure our AI systems behave safely and align with organisational values.

You will be responsible for designing novel safety evaluation frameworks, curating high-quality data for robust evaluations and training, prototyping new safety capabilities, and developing safety-focused fine-tuning algorithms.

We’re looking for outstanding individuals with deep expertise in AI safety who can translate research insights into practical solutions while being a strong communicator and collaborative teammate.

The ideal candidate takes the initiative in exploring new safety methodologies and enjoys building world-class, trustworthy AI experiences in a fast-paced applied research environment.

Responsibilities:

Leverage expertise in AI safety to uncover potential risks and develop novel mitigation strategies, including alignment techniques, constitutional AI approaches, RLHF, and robustness improvements for large language models.

Create and implement comprehensive evaluation frameworks and red-teaming methodologies to assess model safety across diverse scenarios, edge cases, and potential failure modes.

Build automated safety testing systems, generalise safety solutions into repeatable frameworks, and write efficient code for safety model pipelines and intervention systems.

Maintain a user-oriented perspective by understanding safety needs from user perspectives, validating safety approaches through user research, and serving as a trusted advisor on AI safety matters.

Track advances in AI safety research, identify relevant state-of-the-art techniques, and adapt safety algorithms to drive innovation in production systems serving millions of users.

Embody our culture and values.

Qualifications:

Required Qualifications:

Bachelor’s Degree in Computer Science, or related technical discipline AND 4+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience.

Preferred Qualifications:

Bachelor’s Degree in Computer Science or related technical field AND 8+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR Master’s Degree in Computer Science or related technical field AND 6+ years technical engineering experience with coding in languages including, but not limited to, C, C++, C#, Java, JavaScript, or Python OR equivalent experience.

Experience prompting and working with large language models.

Experience writing production-quality Python code.

Demonstrated interest in Responsible AI.

Software Engineering IC4 – The typical base pay range for this role across the U.S. is USD $119,800 – $234,700 per year.

Software Engineering IC5 – The typical base pay range for this role across the U.S. is USD $139,900 – $274,800 per year.

This position will be open for a minimum of 5 days, with applications accepted on an ongoing basis until the position is filled.

Microsoft is an equal opportunity employer.

XML job scraping automation by YubHub

We work on the bleeding edge and leverage the most powerful pretrained models and algorithms, making it critical that we ensure our AI systems behave safely and align with organisational values.

You will be responsible for designing novel safety evaluation frameworks, curating high-quality data for robust evaluations and training, prototyping new safety capabilities, and developing safety-focused fine-tuning algorithms.

We're looking for outstanding individuals with deep expertise in multimodal AI safety who can translate research insights into practical solutions while being a strong communicator and collaborative teammate.

The ideal candidate takes the initiative in exploring new safety methodologies and enjoys building world-class, trustworthy AI experiences in a fast-paced applied research environment.

Microsoft's mission is to empower every person and every organisation on the planet to achieve more.

As employees we come together with a growth mindset, innovate to empower others, and collaborate to realise our shared goals.

Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Responsibilities:

Leverage expertise in multimodal safety to uncover potential risks and develop novel mitigation strategies, including alignment techniques and robustness improvements for multimodal large language models.

Create and implement comprehensive evaluation frameworks and red-teaming methodologies to assess model safety across diverse scenarios, edge cases, and potential failure modes.

Build automated safety testing systems, generalise safety solutions into repeatable frameworks, and write efficient code for safety pipelines and intervention systems.

Maintain a user-oriented perspective by understanding safety needs from user perspectives, validating safety approaches through user research, and serving as a trusted advisor on multimodal safety matters.

Track advances in multimodal safety research, identify relevant state-of-the-art techniques, and adapt safety algorithms to drive innovation in production systems serving millions of users.

Embody our culture and values.

XML job scraping automation by YubHub

We work on the bleeding edge and leverage the most powerful pretrained models and algorithms, making it critical that we ensure our AI systems behave safely and align with organisational values.

You will be responsible for designing novel safety evaluation frameworks, curating high-quality data for robust evaluations and training, prototyping new safety capabilities, and developing safety-focused fine-tuning algorithms.

We’re looking for outstanding individuals with deep expertise in AI safety who can translate research insights into practical solutions while being a strong communicator and collaborative teammate.

The ideal candidate takes the initiative in exploring new safety methodologies and enjoys building world-class, trustworthy AI experiences in a fast-paced applied research environment.

Microsoft’s mission is to empower every person and every organisation on the planet to achieve more.

As employees we come together with a growth mindset, innovate to empower others, and collaborate to realise our shared goals.

Each day we build on our values of respect, integrity, and accountability to create a culture of inclusion where everyone can thrive at work and beyond.

Starting January 26, 2026, MAI employees are expected to work from a designated Microsoft office at least four days a week if they live within 50 miles (U.S.) or 25 miles (non-U.S., country-specific) of that location.

This expectation is subject to local law and may vary by jurisdiction.

XML job scraping automation by YubHub

As a Research Lead on the Training Insights team, you'll develop the strategy for, and lead execution on, how we measure and characterise model capabilities across training and deployment. This is a hands-on leadership role: you'll drive original research into new evaluation methodologies while leading a small team of researchers and research engineers doing the same.

Your work will span the full lifecycle of model development. You'll research and build new long-horizon evaluations that test the boundaries of what our models can achieve, develop novel approaches to measuring emerging capabilities, and deepen our understanding of how those capabilities develop — both during production RL training and after. You'll also take a cross-organisational view, working across Reinforcement Learning, Pretraining, Inference, Product, Alignment, Safeguards, and other teams to map the landscape of model evaluations at Anthropic and identify critical gaps in coverage.

This role carries significant visibility and impact. You'll help shape the evaluation narrative for model releases, contributing directly to how Anthropic communicates about its models to both internal and external audiences. Done well, you will change how the industry measures and understands model capabilities, significantly furthering our safety mission.

Responsibilities:

• Build new novel and long-horizon evaluations
• Develop novel measurement approaches for understanding how model capabilities emerge and evolve during RL training
• Lead strategic evaluation coverage across the company
• Shape the evaluation narrative for model releases
• Lead and mentor a small team of researchers and research engineers, setting research direction and fostering a culture of rigorous, creative research
• Design evaluation frameworks that balance scientific rigor with the practical demands of production training schedules
• Build and maintain relationships across Anthropic's research organisation to ensure evaluation insights inform training and deployment decisions
• Contribute to the broader research community through publications, open-source contributions, or external engagement on evaluation best practices

You may be a good fit if you:

• Have significant experience designing and running evaluations for large language models or similar complex ML systems
• Have led technical projects or teams, either formally or through sustained ownership of critical research directions
• Are equally comfortable designing experiments and writing code—you can move between research and implementation fluidly
• Think strategically about what to measure and why, not just how to measure it
• Can synthesise information across multiple teams and workstreams to form a coherent picture of model capabilities
• Communicate complex technical findings clearly to both technical and non-technical audiences
• Are results-oriented and thrive in fast-paced environments where priorities shift based on research findings
• Care deeply about AI safety and want your work to directly influence how capable AI systems are developed and deployed

Strong candidates may also have:

• Experience building evaluations for long-horizon or agentic tasks
• Deep familiarity with Reinforcement Learning training dynamics and how model behaviour changes during training
• Published research in machine learning evaluation, benchmarking, or related areas
• Experience with safety evaluation frameworks and red teaming methodologies
• Background in psychometrics, experimental psychology, or other measurement-focused disciplines
• A track record of communicating evaluation results to inform high-stakes decisions about model development or deployment
• Experience managing or mentoring researchers and engineers

Representative projects:

• Designing and implementing a suite of long-horizon evaluations that test model capabilities on tasks requiring sustained reasoning, planning, and tool use over extended interactions
• Building systems to track capability development across RL training checkpoints, surfacing insights about when and how specific capabilities emerge
• Conducting a cross-org audit of evaluation coverage, identifying blind spots, and prioritising new evaluations to fill critical gaps across Pretraining, RL, Inference, and Product
• Developing the evaluation methodology and narrative for a major model release, working with research leads and communications to clearly characterise model capabilities and limitations
• Researching and prototyping novel evaluation approaches for capabilities that are difficult to measure with existing benchmarks
• Leading a team effort to build reusable evaluation infrastructure that serves multiple teams across the research organisation

Logistics

Education requirements: We require at least a Bachelor's degree in a related field or equivalent experience. Location-based hybrid policy: Currently, we expect all staff to be in one of our offices at least 25% of the time. However, some roles may require more time in our offices repsectively.

Visa sponsorship: We do sponsor visas!

XML job scraping automation by YubHub