Mohd R.

Key Skills

Software

Scale AI

Top Subject Matter

LLM training and evaluation for code generation (RLHF)

Legal Services & Contract Review

Regulatory Compliance & Risk Analysis

Top Data Types

Text

Document

Top Task Types

RLHF

Freelancer Overview

LLM Training Engineer (Freelance) | Outlier AI (Scale AI). Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Scale AI. Education includes Bachelor of Technology, Delhi Technological University (DTU) (2026) and Higher Secondary Certificate, Dev Samaj Modern School No.2 (2021). AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including RLHF, Prompt-Response Writing, and SFT.

Labeling Experience

LLM Evaluation Engineer (Freelance) - Outlier AI (Scale AI)

Scale AITextRLHF

Served as an LLM Training Engineer for evaluating and improving AI coding tasks within RLHF-based training workflows. Conducted hands-on analysis of complex frontend, backend, full-stack, and scripting outputs to improve task quality and correctness. Applied prompt engineering, rubric-based evaluation, and code review practices to ensure instruction adherence and robust edge-case handling. • Evaluated 25+ complex AI coding tasks across multiple workflow categories to support RLHF LLM training pipelines. • Engineered prompt-response pairs with 40+ test cases and 20+ rubric checks per task to validate correctness and compliance. • Performed 90+ hours of independent QA on AI-generated code, identifying logical inconsistencies and requirement gaps. • Utilized JavaScript and React.js knowledge to assess and improve AI-generated solutions and evaluation artifacts.

2026 - Present

LLM Training Engineer (Freelance) | Outlier AI (Scale AI)

Scale AIRLHF

Freelance LLM Training Engineer evaluating and improving complex AI coding tasks to support RLHF-based LLM training pipelines. Engineered structured prompt-response pairs with test cases and rubric checks to verify correctness, instruction adherence, and edge-case handling. Performed independent QA by flagging logical inconsistencies and requirement gaps beyond automated tests. • Reviewed 25+ complex frontend, backend, full-stack, and scripting coding workflows • Created 40+ test cases and 20+ rubric checks per task for systematic scoring • Conducted 90+ hours of QA on AI-generated code outputs • Ensured findings improved task quality for RLHF model training and evaluation

2026 - Present

Education

Work History