AI Agent Trajectory Annotator and Reviewer
$20 - $30 per hourBespoke Labs
Type: Contract, hourly
Location: Remote
Hours: 20–30 per week
Pay: $20–30/hour, based on experience and language coverage
Start: Immediate
ABOUT THE ROLE
We evaluate how well advanced AI coding agents solve real engineering problems. An agent is given a real open source codebase inside a container and a hard task, then works on its own for 80 to 250 steps. A trajectory is the full record of that run — every command, result, and decision.
You will do two jobs, and you should expect either on any given day.
•Annotate — Read a trajectory nobody has looked at yet and judge it step by step.
• Review — Take an existing annotation, written by our AI tooling or another person, and confirm, correct, or reject it.
TASKS YOU'LL SEE
• Feature build — Add a working feature to a live library without breaking anything that already worked.
• Rebuild — Work out what a compiled tool does by running it, then rebuild it to match its output, exit codes, and file effects.
• Bug hunt — Find and fix twenty undocumented bugs across a dozen files with no test suite, then record what caused them.
Mostly Python and Go, with some Rust, C, and Ct+. A trajectory runs about 100 steps.
WHAT YOU JUDGE IN A TRAJECTORY
• Was the command right for the state the environment was actually in?
• Did the agent read the previous output correctly?
• Was the step wrong, or only inefficient — these are scored differently.
• Where did the run first go off course — usually earlier than where it visibly broke.
• Did the agent notice its own mistake and recover, or keep building on a false assumption?
• Did it game the grader instead of solving the task (e.g., weakening a test or hardcoding an expected value)?
WHAT WE NEED FROM YOU
• Experience — 2+ years in software engineering, DevOps, or site reliability, with real debugging in real codebases.
• Languages — Strong in Python or Go, and able to read a language you've never used.
• Linux — Comfortable with logs, running processes, build failures, and containers.
• Workflow — Everyday Git, diffs, pull requests, and issue tracking.
• Debugging — Able to work with no test suite and no error message pointing at the cause.
• Focus — Able to hold context across a long run, because step 74 can depend on step 12.
• Writing — Clear English, since every judgement needs an explanation another engineer can check.
$43k - $60k
...Life and Health insurance licenses How to Apply: Please review our website below, and if you think our office is a good fit, and... ...sales, we want to hear from you! David Christy - State Farm Agent is an equal opportunity employer and encourages applications from...SuggestedFor contractorsWork at officeFlexible hoursState Farm
Pullman, WA3 days ago- ...p.m. If staffing allows, TM's can work 8:30 – 5:30 with 1 hour lunch or 9 – 5:30 with half hour lunch. I have been a State Farm agent since 1994. We currently have 15 team members at our agency. Apply Now And Let Us Put You On The Path To Success State Farm...SuggestedFor contractorsWork at office
David Christy - State Farm Agent
Pullman, WA23 hours ago - ...Life and Health insurance licenses How to Apply: Please review our website below, and if you think our office is a good fit, and... ...we want to hear from you! David Christy - State Farm Agent is an equal opportunity employer and encourages applications from...SuggestedWork at officeFlexible hours
David Christy - State Farm Agent
Pullman, WA9 days ago - NO EXPERIENCE REQUIRED – PAID TRAINING PROVIDED – JOB SECURITY The Postal Service is the largest government related agency in terms of employees. The Postal Service currently employs nearly 1 million people and is hiring nationwide. There is NO experience required, ...SuggestedFull time
$26.47 - $43.62 per hour
The Postal Service is the largest government-related agency, employing nearly 1 million people, and is currently hiring nationwide with many positions available. Job Description Clerk – Clerks sell stamps, take incoming mail, and sort and distribute mail in addition...SuggestedHourly payFull timeCurrently hiringWork at office$17 per hour
Retail Banking TellerZions Bank recognizes that its success comes from the dedication, experience and talents of its diverse employee base. As we usher in the next generation of banking, we're committed to being the premier employer of choice. We're proud to have ranked...Flexible hoursZions Bank
Moscow, ID1 day ago$23.47 - $38.62 per hour
Role Overview USPS is actively accepting applications for Mail Handler Assistants nationwide. This position is open to candidates of all experience levels, with comprehensive training provided to help you succeed. Join a dynamic work environment where you will interact...Hourly payFlexible hoursPostal Jobs Resource
Moscow, IDmore than 2 months ago- NO EXPERIENCE REQUIRED – PAID TRAINING PROVIDED – JOB SECURITY The Postal Service is the largest government related agency in terms of employees. The Postal Service currently employs nearly 1 million people and is hiring nationwide. There is NO experience required, ...Full time
$23.47 - $38.62 per hour
Role Overview USPS is accepting applications for PSE Mail Processing Clerks nationwide. This role is vital to ensuring the timely and accurate processing of mail. USPS provides comprehensive training to help you succeed, even if you have no prior experience. Position...Hourly payPostal Jobs Resource
Moscow, IDmore than 2 months ago- POSTAL MAIL PROCESSOR NO EXPERIENCE REQUIRED – PAID TRAINING PROVIDED – JOB SECURITY The Postal Service is the largest government related agency in terms of employees. The Postal Service currently employs nearly 1 million people and is hiring nationwide. There is...Full time
US Postal Service
Moscow, ID7 days ago $23.47 - $38.62 per hour
Role Overview USPS is accepting applications for Assistant Rural Carriers nationwide. In this role, you deliver and collect packages along designated suburban and rural routes, often using your personal vehicle. The position primarily involves working on weekends and...Hourly payWeekend workPostal Jobs Resource
Moscow, IDmore than 2 months ago$18 - $20 per hour
Pullman, Washington Full time JR103054 About the Role: As the first point of contact for most clients, Tellers play a key role in delivering on the bank's Breakthrough Client Service Standards. With guidance from the Branch Manager and Assistant Branch Manager...Full timeLocal areaNight shiftColumbia Bank (WA, OR & ID)
Pullman, WA23 hours ago- ABOUT Act as our eyes and ears in the sky, mapping coasts and ports for Navy intelligence. Gain extensive training in radar, sonar, and air traffic communications. If you feel more at home above the sea than on it, a career in aviation might be for you. Below are some...Full timePart time
U.S. Navy
Moscow, ID4 days ago - ...project files and project tracking records such as time reporting, financial records, schedules, budgets and summary spreadsheets. Review project proposals for accuracy and adherence to style guidelines. Administer the flow of project documents between internal and external...ApprenticeshipWork at officeWorldwideFlexible hours
Schweitzer Engineering Laboratories, Inc.
Pullman, WA2 days ago
Do you want to receive more vacancies?
Subscribe and receive similar vacancies to AI Agent Trajectory Annotator and Reviewer. Be the first to apply!
