Job Summary
Mercor is seeking Software Engineering, Data Science, and Systems Design Experts (Ruby) to evaluate and improve AI-generated coding outputs.
In this role, you will assess how well AI systems reason about code, solve technical problems, and explain complex engineering concepts. Your feedback will directly improve the reliability and quality of AI tools used by developers worldwide.
Key Responsibilities
- Evaluate AI-generated responses to coding and software engineering queries.
- Assess correctness, reasoning quality, clarity, and completeness.
- Execute and validate code to verify accuracy and outputs.
- Identify bugs, inefficiencies, and logical flaws in model-generated solutions.
- Analyze code quality, readability, and algorithmic soundness.
- Provide structured annotations highlighting strengths and areas for improvement.
- Ensure outputs align with engineering best practices and evaluation guidelines.
Requirements
- Bachelor’s, Master’s, or PhD in Computer Science or a related field.
- 5+ years of professional experience in software engineering or similar roles.
- Strong expertise in Ruby programming.
- Ability to solve medium to hard algorithmic problems (e.g., LeetCode/HackerRank).
- Experience contributing to open-source projects (with merged pull requests).
- Familiarity with using LLMs in coding workflows and understanding their limitations.
- Strong analytical skills and attention to detail.
Preferred Qualifications
- Experience with RLHF, AI evaluation, or annotation workflows.
- Background in competitive programming.
- Experience reviewing production-level code.
- Familiarity with multiple programming languages or paradigms.
- Ability to explain complex technical concepts clearly.
What Success Looks Like
- Identifying incorrect logic, edge cases, and inefficiencies in AI-generated code.
- Improving clarity, correctness, and robustness of AI outputs.
- Delivering consistent, high-quality evaluation insights.
Contract & Payment
- Employment Type: Contract (Freelance)
- Location: Remote (Worldwide)
- Pay: $60 – $100 per hour
- Payments are made weekly via Stripe or Wise.
Note: This is an independent contractor role. Project duration may vary based on performance and project needs.