Remote AI Coding Evaluator - Software Engineer Tasks

HumanitApp; Pakistan; Remote; PKR 7,624,000 - 11,436,000; Full time

Benefits offered by this job

Fully remote

Job summary

Turing is seeking experienced Software Engineers to support AI training and evaluation, focusing on reviewing AI-generated coding solutions for real software tasks. You will assess agent runs, measure correctness and efficiency, and provide evidence-based feedback to improve AI-assisted software development.

The role is fully remote, contractor-based, with a pay- per-task model ($25 per approved task) and a defined 1-month engagement.

Qualifications

• Minimum 3+ years of overall experience.
• Proficiency with shell commands, Git and Docker.
• Comfortable running and testing real-world projects locally.

Responsibilities

• Review and rate AI coding solutions across real software tasks.
• Evaluate code correctness, efficiency, safety, and quality.
• Provide structured ratings and evidence-based feedback to improve AI-assisted software development.
• Rank three agent runs and write concise rationales.

Skills

Shell commands

Git

3+ years experience

Basic software pipelines

Tools

Docker

Job description

Turing is seeking experienced Software Engineers to support AI training and evaluation, focusing on reviewing AI-generated coding solutions for real software tasks. You will assess agent runs, measure correctness and efficiency, and provide evidence-based feedback to improve AI-assisted software development.

The role is fully remote, contractor-based, with a pay- per-task model ($25 per approved task) and a defined 1-month engagement.