Frontier AI Evaluation Engineer | RL & Environments

Primeintellect

San Francisco (CA)

Hybrid

USD 150,000 - 350,000

Full time

14 days+

Get a reply from this employer

Your resume and cover letter, tailored to exactly what they’re hiring for.

Get past ATS filters

Benefits offered by this job

Cash compensation & equity
Remote or SF office
Visa sponsorship & relocation
Team off-sites & hackathons
Learning opportunities

Job summary

Prime Intellect is building the open frontier AI platform that unifies compute, environments, evaluations, and secure sandboxes for frontier-scale model training and deployment. We seek engineers to design tasks, environments, and evaluation pipelines enabling researchers to push the limits of RL and agentic systems.

You will work with researchers to diagnose failures, refine tasks, and improve scoring and verification to advance autonomous research at scale.

Qualifications

  • Strong Python software engineering skills and data pipeline experience.
  • Hands-on with language models or agents and how data influences behavior.
  • Ability to inspect complex data and turn questions into tests.
  • Record of leading technical projects from prototype to validation.

Responsibilities

  • Design and build challenging evaluations for coding and long-horizon agents.
  • Build executable environments in Verifiers with realistic tasks and clear success criteria.
  • Develop and test scoring logic and verifiers, examining reward design.
  • Trace failures through model outputs to distinguish model limits from env issues.
  • Build and scale RL data pipelines that generate coding and agentic tasks.
  • Collaborate with RL researchers to test task/training data effects on held-out tasks.

Skills

Python
Data pipelines
Evaluation systems
ML workflows
Research collaboration

Tools

Verifiers

Job description

Prime Intellect is building the open frontier AI platform that unifies compute, environments, evaluations, and secure sandboxes for frontier-scale model training and deployment. We seek engineers to design tasks, environments, and evaluation pipelines enabling researchers to push the limits of RL and agentic systems.

You will work with researchers to diagnose failures, refine tasks, and improve scoring and verification to advance autonomous research at scale.

Get your free, confidential resume review.

or drag and drop your file here.

Similar jobs

Similar jobs worth comparing

Frontier AI Evaluation Engineer (RL & Data Pipelines)
Frontier AI Evaluation Engineer (RL & Data Pipelines)

Prime Intellect, Inc. • San Francisco (CA)

Hybrid
USD 150,000 - 350,000
Cash compensation range
Remote or on-site SF office
Visa sponsorship
+1
Frontier AI Applied Researcher
Frontier AI Applied Researcher

Prime Intellect, Inc. • New York (NY)

Remote
USD 150,000 - 300,000
Cash Compensation Range of $150-300k +
Equity incentives
Flexible Work (SF, NY, London, or rem)
+3
Remote RL Research Engineer - Frontier AI Platform
Remote RL Research Engineer - Frontier AI Platform

Prime Intellect, Inc. • San Francisco (CA)

Hybrid
USD 150,000 - 350,000
Cash compensation
Remote or in-person options
Visa sponsorship
+1
Frontier RL Infrastructure Engineer
Frontier RL Infrastructure Engineer

Prime Intellect, Inc. • San Francisco (CA)

Remote
USD 150,000 - 350,000
Equity incentives
Remote or SF office
Visa sponsorship
+2
Applied Researcher - Frontier AI & RL Systems (Remote)
Applied Researcher - Frontier AI & RL Systems (Remote)

Prime Intellect AI • San Francisco (CA)

Hybrid
USD 150,000 - 300,000
Visa sponsorship
Relocation support
Professional development budget
+2
Frontier Robotics Applied Researcher (Remote)
Frontier Robotics Applied Researcher (Remote)

Prime Intellect • United States

Remote
USD 150,000 - 300,000
Cash compensation and equity
Remote work options
Visa sponsorship & relocation
+2
Remote Research Engineer - Frontier AI Platform
Remote Research Engineer - Frontier AI Platform

Prime Intellect • United States

Remote
USD 150,000 - 350,000
Visa sponsorship
Relocation assistance
Remote work option
+2
Remote Research Engineer — AI Evaluation & RL Data Pipelines
Remote Research Engineer — AI Evaluation & RL Data Pipelines

Prime Intellect AI • San Francisco (CA)

Hybrid
USD 150,000 - 350,000
Salary + equity
Remote or SF Office
Visa sponsorship
+2
Research Engineer: RL Environments for Frontier AI
Research Engineer: RL Environments for Frontier AI

Prime Intellect, Inc. • United States

Remote
USD 150,000 - 350,000
Quarterly off-sites
Hackathons
Conferences
+1
Frontier Robotics AI Researcher (Remote)
Frontier Robotics AI Researcher (Remote)

Prime Intellect AI • San Francisco (CA)

Remote
USD 150,000 - 300,000
Cash compensation
Equity incentives
Flexible work locations
+3