C++ Systems Engineer for AI Model Evaluation & Code Review
Crossing Hurdles
United States
On-site
USD 82,656 - 137,760
Part time
14 days+
Application generator
Stand out for this role — generate a tailored resume and cover letter in about a minute.
Get past ATS filters
Job summary
A technology evaluation firm is seeking software engineering experts with a strong background in C++ and data science. This role involves evaluating LLM-generated content, conducting accuracy assessments, and ensuring alignment with technical standards. Candidates should hold at least a bachelor's degree in computer science and have real-world experience in software engineering. The position offers flexibility between full-time or part-time commitments and can be performed remotely.
Qualifications
Real-world experience in software engineering or related technical roles.
Ability to solve HackerRank or LeetCode Medium and Hard–level problems independently.
Experience contributing to open-source projects.
Prior experience with RLHF, model evaluation, or data annotation work preferred.
Responsibilities
Evaluate LLM-generated responses for accuracy and completeness.
Conduct fact-checking using trusted public sources.
Conduct accuracy testing by executing code.
Annotate model responses for strengths and improvements.
Assess code quality and alignment with guidelines.
Skills
C++ programming language
Problem-solving (HackerRank, LeetCode)
Attention to detail
Complex technical reasoning evaluation
Experience with LLMs
Education
BS, MS, or PhD in Computer Science
Job description
A technology evaluation firm is seeking software engineering experts with a strong background in C++ and data science. This role involves evaluating LLM-generated content, conducting accuracy assessments, and ensuring alignment with technical standards. Candidates should hold at least a bachelor's degree in computer science and have real-world experience in software engineering. The position offers flexibility between full-time or part-time commitments and can be performed remotely.