Staff+ Research Engineer, RL Data Platform

Details

Anthropic's RL Data Platform team builds the systems that produce, move, and serve the human data Claude learns from, including feedback interfaces, pipelines that turn raw feedback into training signals, and tooling for launching, monitoring, and inspecting data collection. This full-stack role involves designing and shipping web interfaces for expert annotators, building backend services and data pipelines, and partnering directly with RL researchers. The role requires end-to-end project ownership, architectural judgment, and a strong focus on reliability, data quality, latency, and usability.

Responsibilities

• Design, build, and operate feedback and data collection interfaces for human annotators, domain experts, and internal researchers.
• Build and maintain backend services, APIs, and pipelines that route model samples to humans and return structured feedback to training.
• Own the reliability, latency, and usability of systems running continuously against live model endpoints.
• Partner with RL researchers to translate data requirements into collection campaigns and supporting tooling.
• Build dashboards, monitoring, and inspection tools for data quality and throughput.
• Identify and remove bottlenecks between requested data and its inclusion in the training mix.

Requirements

• Strong full-stack engineering skills with production experience in TypeScript, React, and Python.
• Experience designing and operating backend services and data pipelines used by other teams.
• Experience owning projects end-to-end, from ambiguous briefs through production delivery.
• Ability to work directly with technical stakeholders whose needs change frequently, and to assess when work is or is not worth building.
• Effective use of AI tools in day-to-day work.
• Care for the societal impacts of the work.
• Bachelor's degree or equivalent combination of education, training, and experience.

Preferred Qualifications

• Experience building annotation, labeling, evaluation, or other human-in-the-loop data tooling.
• Experience with RLHF, preference data, or human-feedback pipelines for machine-learning systems.
• Experience shipping researcher-facing or expert-facing internal tools and improving their usability.
• Experience running experiments on data collection interfaces to improve data quality.
• Experience working with crowdworker or expert vendor platforms at scale.
• Familiarity with how large language models are trained and evaluated.

Benefits

Anthropic offers competitive compensation and benefits, optional equity donation matching, generous vacation and parental leave, flexible working hours, and office spaces for collaboration. Anthropic sponsors visas where possible and retains an immigration lawyer to assist with visa sponsorship. Staff are expected to work from an Anthropic office at least 25% of the time, although some roles may require more office time.