Remote freelance data annotator for Innodata India — reviewing and evaluating AI model responses for quality, grammar, coherence, and accuracy to improve LLMs. 5-6 hrs/day, ₹350/hr. B2+ English required.
Annotator - STEM
Job description
About the Role
Annotators are the core builders of SkillsBench. You will design and write AI evaluation tasks — structured challenges given to large language model (LLM) agents running inside automated environments. Each task tests whether an AI agent performs significantly better when given domain-specific knowledge vs. without it.
What You Will Do
- Write clear, unambiguous task instructions defining exactly what an AI agent must produce
- Create reference solutions that demonstrate the correct approach and pass all automated checks
- Write human-readable verifier descriptions listing every check the automated test suite will run
- Author domain-specific skill files teaching AI agents conventions, workflows, and edge cases
- Work within task structure (instruction, environment, solution, tests) following Turing's quality standards
Domains
- Power Systems & Control
- Cybersecurity
- Network & System Engineering
Requirements
- Bachelor's degree or higher in Computer Science, Engineering, Finance, Data Science, Linguistics, or related field
- 1–3 years of hands-on practical expertise in at least one domain
- Strong written English; ability to write precise, unambiguous instructions
- Comfort reading and producing JSON, DOCX, XLSX, Markdown outputs
Offer Details
- 40 hours per week with 4-hour PST overlap required
- Contractor assignment (no medical/paid leave)
- 2-month contract; expected start: next week
You will be redirected to the company's website to complete your application.