Get Started
Hunting for you, 24x7Get the iPhone app

Your hunt runs in your pocket, and tells you the moment a strong match opens.

Download on theApp Store

Benchmark design jobs

20 open roles for benchmark design, updated continuously as employers post them.

This market right now

Of the 10 that state pay, the middle one advertises $96 – $125 an hour.

Hiring most here right now:

Counted across the roles Frontrunner has open right now.

20 open roles
RemoteJobsOnePosted 2 days ago

Member of Technical Staff, Coding Agent Research & Evaluations – Remote (Worldwi

RemotePrincipal$600,000 – $1,300,000 a year

A fully remote, full-time, principal-level role designing benchmarks and evaluations for frontier coding agents, open to candidates in 55 countries. It suits engineers with research and evaluation experience who can explain findings clearly.

PythonC++Benchmark designModel evaluation +7
We reach hiring manager, team lead and founder Power Apply
MpathicPosted 2 days ago

Machine Learning Engineer, Evaluation

United StatesRemoteMid level

Full-time remote mid-level role in the US building evaluation tooling and benchmarks for clinical-conversation AI at mpathic. Best suited to ML engineers with two to five years of experience who can design rigorous evaluations.

PythonMachine LearningGenerative AIEvaluation Metrics +12
We reach founder, head of talent and hiring manager Power Apply
Power Apply

Skip the portal. Reach the person hiring.

One tap and Frontrunner finds who hires for the role, writes in your voice, and sends from your own Gmail and LinkedIn.

Finds themHiring manager
WritesIn your voice
SendsGmail and LinkedIn
Tracks repliesIn one place
RemoteJobsOnePosted in November 2026

Member of Technical Staff, Coding Agent Research & Evaluations – Remote (Worldwi

Canada · France · Germany · India · Netherlands · PhilippinesRemotePrincipal$200,000 – $260,000 a year

A senior remote research role building benchmarks and evaluation methods for frontier coding agents, open to engineers with three or more years of experience. It suits engineers who combine software engineering with model evaluation and analysis.

PythonC++Large Language ModelsCoding Agents +6
We reach recruiter, hiring manager and head of the team Power Apply
RemoteJobsOnePosted 3 days ago

Member of Technical Staff, Cortex Lab (applied AI research)

RemoteSenior$200,000 – $250,000 a year

A full-time, remote applied AI research role focused on evaluating and improving LLM agents in enterprise workflows. It suits researchers and engineers with agent evaluation and Python experience.

LLM evaluationAI agentsAgent evaluationBenchmark design +9
We reach founder, head of talent and hiring manager Power Apply

Every new role is checked against your skills, experience, place and pay. If they can't hire you, it never reaches you.

ЯндексPosted 4 days ago

Data scientist

Data scientist role at Yandex covering generative model evaluation, ad moderation, anti-fraud and metrics work, for candidates with strong Python, SQL and statistics skills. Pay and location are not stated in the listing.

PythonSQLYQLMachine learning +9
We reach team lead, recruiter and a recent hire on the team Power Apply
OpenTrain AIPosted 4 days ago

Member of Technical Staff, Coding Research

United Arab Emirates · ArgentinaRemotePrincipal$87 – $125 an hour

Part-time remote contract role for a research engineer building benchmarks and evaluation frameworks for coding models and agents, paying USD 86.54-125 per hour and open to applicants in 52 countries.

LLMsCoding evaluationAI evaluationML systems +7
We reach recruiter, hiring manager and head of the team Power Apply
OpenTrain AIPosted 4 days ago

Member of Technical Staff, Coding Research (English)

United Arab Emirates · ArgentinaRemotePrincipal$96 – $125 an hour

Remote part-time contract role for engineers with at least three years of experience who build evaluations and benchmarks for coding agents, paying USD 96.15-125 per hour.

LLMsCoding evaluationAI evaluationML systems +6
We reach team lead, recruiter and a recent hire on the team Power Apply
Hunting 24x7
305,808

new roles this week. Frontrunner reads every one for you.

It never stops looking, and it only wakes you for the good ones.

OpenTrain AIPosted 5 days ago

Member Technical Staff Coding Agent Research Evaluation

United Arab Emirates · ArgentinaRemotePrincipal$96 – $125 an hour

A remote, part-time contract role designing benchmarks and evaluation methods for coding agents, suited to engineers with assessment and software engineering experience.

PythonC++Coding AgentsLarge Language Models +8
We reach team director, hiring manager and recruiter Power Apply
CleraPosted 7 days ago

Expert Talent Pool, Evals and Benchmarks (Associate)

RemoteMid level30 – 60 an hour

A fully remote, hourly talent pool role for early-career specialists who design AI model evaluations, write rubrics and grade model outputs. It suits people with up to five years of experience in QA, assessment, data analysis or research support.

Rubric designBenchmark designAI model evaluationLLM evaluation +10
We reach founder, head of talent and hiring manager Power Apply
ElevenLabsPosted in November 2026

Research Engineer

London, United Kingdom · New York, United States · San Francisco, United States · Warsaw, PolandRemote or on-siteMid level

A full-time remote research engineer role at ElevenLabs focused on training and evaluating audio AI models, for engineers with at least three years of machine learning experience.

Machine learningModel trainingPost-trainingData curation +5
We reach technical recruiter, engineering manager and a team member Power Apply
ElevenlabsPosted in November 2026

Research Engineer

London, United Kingdom · New York, United States · San Francisco, United States · Warsaw, PolandRemote or on-site

A remote research engineer role at ElevenLabs, training and evaluating audio AI models. It suits engineers with 3+ years in machine learning who can show strong past work rather than formal credentials.

Machine learningModel trainingPost-trainingData curation +6
We reach talent partner, hiring manager and a senior teammate Power Apply
FreelancerPosted 13 days ago

Design Original ML Benchmark Challenges (ML Experts ONLY)

Remote

A remote freelance project for ML experts to design reproducible machine learning benchmark challenges for an agent evaluation platform, paid USD 200 per accepted challenge.

Machine learningPythonPandasscikit-learn +12
We reach technical recruiter, engineering manager and a team member Power Apply
Software EstrategicoPosted 15 days ago

Senior AI Quality Engineer (LLM Evaluation & Automation)

WorldwideRemoteSenior

A senior remote role open worldwide for an engineer who builds and runs evaluation harnesses and release gates for LLM-based agents.

LLM EvaluationTest AutomationBenchmark DesignRegression Testing +6
We reach recruiter, hiring manager and head of the team Power Apply
Software EstrategicoPosted 15 days ago

Agent Quality / Evals Engineer

WorldwideRemote

Full-time remote role owning the evaluation harness and release quality gate for AI agents, with thresholds that block regressions. Suits engineers experienced in evaluating LLM and other non-deterministic systems who can automate benchmarks in CI.

LLM evaluationBenchmark designTest automationCI/CD +4
We reach talent partner, hiring manager and a senior teammate Power Apply
FutureSearchPosted 17 days ago

Research Scientist

Remote, GlobalRemote$125,000 – $225,000 a year

Fully remote research scientist role at a seed-stage AI forecasting startup, with a US salary range of $125k to $225k. Suits quantitative researchers who study modern AI systems and can make fast progress on open problems.

AI researchLLM agentsBenchmark designForecasting +5
We reach recruiter, hiring manager and head of the team Power Apply
TetherPosted 18 days ago

AI Research Engineer (Multi-Modal & Vision) - 100% Remote Worldwide

WorldwideRemote

A full-time, 100% remote research engineering role open worldwide, focused on training, evaluating, and deploying vision-language models on Tether's AI model team.

Vision-Language ModelsMultimodal LearningModel TrainingPost-Training +12
We reach CTO, engineering lead and technical recruiter Power Apply
RemoteJobsOneDate not stated

Member of Technical Staff, Coding Agent Research & Evaluations

Remote in a region — 6 countriesRemoteMid level$200,000 – $260,000 a year

A full-time, fully remote role measuring and improving coding agents, suited to mid-level engineers with evaluation and machine learning experience.

PythonC++Machine LearningLarge Language Models +8
We reach hiring manager, recruiter and the person who posted the job Power Apply
Joblet-AIDate not stated

AI Research Engineer

IndiaRemote$200,000 – $260,000 a year

A full-time remote role for engineers with three or more years of experience who design benchmarks and evaluation methods for coding agents. It suits people who enjoy research, rigorous measurement and software engineering.

PythonC++LLM EvaluationBenchmark Design +10
We reach CTO, engineering lead and technical recruiter Power Apply
TuringDate not stated

Software Engineer

Remote · Global - Remote; United StatesRemote

A remote software engineering role at Turing for experienced Python and Django engineers who build evaluation infrastructure for frontier AI labs.

PythonDjangoPostgreSQLCelery +12
We reach hiring manager, team lead and founder Power Apply

Browse by role

Jobs by role and place

Remote jobs by role and country

Browse by location

Browse by work mode

Browse by employment type

Browse by seniority

Remote roles

Browse by skill

Browse by industry

Browse by product

Companies hiring