Anthropic
Anthropic’s mission is to create reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our users and for society as a whole. Our team is a quickly growing group of committed researchers, engineers, policy experts, and business leaders working together to build beneficial AI systems.
About The Role As a Technical Program Manager for model evaluations, you’ll own end-to-end coordination of our evaluation ecosystem—building a feedback loop from shaping eval strategy during early model development through launch execution. You’ll be the critical bridge between Research, Product, Marketing, and Engineering teams. This role sits at the intersection of frontier AI research and product launches. Evals are an important part of how we measure whether our models meet the bar—for capability, safety, and competitive positioning. Beyond launch coordination, you’ll help scale our evals ecosystem: from early-stage model evals for RL environments, to the systems and infrastructure on which evals run, to tooling that enables the whole pipeline. A strong TPM in this space can immediately reduce chaos during launches while also driving systemic improvements that compound over time.
Key Responsibilities
Standardize how evaluation results are generated, documented, compared across model versions, and communicated to stakeholders
Own end-to-end eval readiness for model launches—tracking which evals are ready, which need scores on past models, and which meet the bar for marketing materials
Establish and enforce clear criteria for eval inclusion: scores on historical models, state-of-the-art performance, and competitor comparisons
Coordinate between research teams, marketing, and product to consolidate eval status into a single source of truth
Maintain a high bar: ensure reported statistics reflect model capabilities in an honest, accurate, and transparent way
Ecosystem Development
Get involved early in model development cycles, helping shape eval plans for RL environments
Partner with research and infrastructure teams to improve underlying evals infrastructure—eval-syncer reliability, results storage and querying, automation capabilities
Drive prioritization of eval tooling enhancements based on researcher needs
Identify patterns across launches and drive systemic fixes rather than point solutions
Work with PMs and researchers to improve and implement high priority evals launches
Maintain and prioritize the eval roadmap—working with cross‑functional teams to identify which new evals are needed for upcoming launches and product requirements
Implement an operating model that reflects an evals environment with increasing complexity
Process & Systems
Build lightweight but rigorous tracking systems—moving key information into structured formats that enable better decision‑making
Create eval dashboards that provide real‑time visibility into training progress on hero evals, enabling earlier intervention when scores look concerning
Document eval processes, requirements, and lessons learned to build institutional knowledge
Coordinate compute allocation for large‑scale evals with infrastructure teams
You May Be a Good Fit If You
Have 5+ years of technical program management experience with a track record of bringing order to chaotic, high‑stakes coordination problems
Possess scientific depth and a very high quality bar for data
Have experience with ML/AI evaluation methodologies, benchmarking, or research quality assurance
Have a background in research operations, scientific publishing, or data quality management
Have previous experience as data analyst, data scientist, or software engineer
Can build trust with research teams by understanding their work deeply enough to add value beyond coordination
Are skilled at cross‑functional coordination involving research, product, marketing, and engineering—navigating competing priorities and driving alignment
Have working familiarity with data analysis tools (SQL, Python, or similar) for querying eval results and building dashboards
Have familiarity with LLM capabilities and limitations and experience working with AI research teams
Excel at written and verbal communication, translating technical nuance for marketing stakeholders while maintaining precision
Thrive in unstructured environments with a bias toward action and a knack for creating clarity in ambiguous situations
Have extremely high ownership and attention to detail
Compensation The expected base compensation for this position is $290,000—$365,000 USD per year. Our total compensation package for full‑time employees includes equity, benefits, and may include incentive compensation.
Deadline to Apply None—applications will be received on a rolling basis.
Logistics
Education requirements: at least a Bachelor’s degree in a related field or equivalent experience.
Location‑based hybrid policy: staff are expected to be in an office at least 25% of the time.
Visa sponsorship: we sponsor visas and will make every reasonable effort to obtain a visa if we make you an offer.
We encourage you to apply even if you do not believe you meet every single qualification.
Guidance on Candidates' AI Usage Learn about our policy for using AI in our application process.
#J-18808-Ljbffr
About The Role As a Technical Program Manager for model evaluations, you’ll own end-to-end coordination of our evaluation ecosystem—building a feedback loop from shaping eval strategy during early model development through launch execution. You’ll be the critical bridge between Research, Product, Marketing, and Engineering teams. This role sits at the intersection of frontier AI research and product launches. Evals are an important part of how we measure whether our models meet the bar—for capability, safety, and competitive positioning. Beyond launch coordination, you’ll help scale our evals ecosystem: from early-stage model evals for RL environments, to the systems and infrastructure on which evals run, to tooling that enables the whole pipeline. A strong TPM in this space can immediately reduce chaos during launches while also driving systemic improvements that compound over time.
Key Responsibilities
Standardize how evaluation results are generated, documented, compared across model versions, and communicated to stakeholders
Own end-to-end eval readiness for model launches—tracking which evals are ready, which need scores on past models, and which meet the bar for marketing materials
Establish and enforce clear criteria for eval inclusion: scores on historical models, state-of-the-art performance, and competitor comparisons
Coordinate between research teams, marketing, and product to consolidate eval status into a single source of truth
Maintain a high bar: ensure reported statistics reflect model capabilities in an honest, accurate, and transparent way
Ecosystem Development
Get involved early in model development cycles, helping shape eval plans for RL environments
Partner with research and infrastructure teams to improve underlying evals infrastructure—eval-syncer reliability, results storage and querying, automation capabilities
Drive prioritization of eval tooling enhancements based on researcher needs
Identify patterns across launches and drive systemic fixes rather than point solutions
Work with PMs and researchers to improve and implement high priority evals launches
Maintain and prioritize the eval roadmap—working with cross‑functional teams to identify which new evals are needed for upcoming launches and product requirements
Implement an operating model that reflects an evals environment with increasing complexity
Process & Systems
Build lightweight but rigorous tracking systems—moving key information into structured formats that enable better decision‑making
Create eval dashboards that provide real‑time visibility into training progress on hero evals, enabling earlier intervention when scores look concerning
Document eval processes, requirements, and lessons learned to build institutional knowledge
Coordinate compute allocation for large‑scale evals with infrastructure teams
You May Be a Good Fit If You
Have 5+ years of technical program management experience with a track record of bringing order to chaotic, high‑stakes coordination problems
Possess scientific depth and a very high quality bar for data
Have experience with ML/AI evaluation methodologies, benchmarking, or research quality assurance
Have a background in research operations, scientific publishing, or data quality management
Have previous experience as data analyst, data scientist, or software engineer
Can build trust with research teams by understanding their work deeply enough to add value beyond coordination
Are skilled at cross‑functional coordination involving research, product, marketing, and engineering—navigating competing priorities and driving alignment
Have working familiarity with data analysis tools (SQL, Python, or similar) for querying eval results and building dashboards
Have familiarity with LLM capabilities and limitations and experience working with AI research teams
Excel at written and verbal communication, translating technical nuance for marketing stakeholders while maintaining precision
Thrive in unstructured environments with a bias toward action and a knack for creating clarity in ambiguous situations
Have extremely high ownership and attention to detail
Compensation The expected base compensation for this position is $290,000—$365,000 USD per year. Our total compensation package for full‑time employees includes equity, benefits, and may include incentive compensation.
Deadline to Apply None—applications will be received on a rolling basis.
Logistics
Education requirements: at least a Bachelor’s degree in a related field or equivalent experience.
Location‑based hybrid policy: staff are expected to be in an office at least 25% of the time.
Visa sponsorship: we sponsor visas and will make every reasonable effort to obtain a visa if we make you an offer.
We encourage you to apply even if you do not believe you meet every single qualification.
Guidance on Candidates' AI Usage Learn about our policy for using AI in our application process.
#J-18808-Ljbffr