Full Stack & Devops & AI
Backend ⚙️Full-Stack 🔄AI/ML 🤖DevOps ☁️
F
faceless
Verified
I'm looking for technical engineers to help create realistic engineering tasks for evaluating AI agents.
This isn’t just prompt writing. The work is more like designing real developer problems inside codebases and environments — things like debugging, fixing integrations, handling edge cases, working with tests, and making tasks verifiable.
The sweet spot is a task that a strong agent can often solve, but not every single time. So we need people who can design challenges that are fair, realistic, and a little messy in the right way.
Best fit is someone with solid software engineering experience who understands code, debugging, environments, and how real-world tasks break. If you’ve worked across backend, full-stack, infra, QA, or AI evaluation, you’d probably be a great fit.
https://snorkel-ai.github.io/Terminus-EC-Training-stateful/portal/docs
Please go through the onboarding material and DM if you're interested
Budget range: $50~$100 per task
Timeine: 1 or 2 tasks perday
Looking for someone who can start immediately
This isn’t just prompt writing. The work is more like designing real developer problems inside codebases and environments — things like debugging, fixing integrations, handling edge cases, working with tests, and making tasks verifiable.
The sweet spot is a task that a strong agent can often solve, but not every single time. So we need people who can design challenges that are fair, realistic, and a little messy in the right way.
Best fit is someone with solid software engineering experience who understands code, debugging, environments, and how real-world tasks break. If you’ve worked across backend, full-stack, infra, QA, or AI evaluation, you’d probably be a great fit.
https://snorkel-ai.github.io/Terminus-EC-Training-stateful/portal/docs
Please go through the onboarding material and DM if you're interested
Budget range: $50~$100 per task
Timeine: 1 or 2 tasks perday
Looking for someone who can start immediately