Raza A.

Key Skills

Software

Other

Top Subject Matter

Large language model training and evaluation (domain-specific LLM optimization)

Legal Services & Contract Review

Regulatory Compliance & Risk Analysis

Top Data Types

Text

Document

Top Task Types

RLHF

Freelancer Overview

Senior LLM Trainer (Supervised Fine-Tuning and RLHF). Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Computer Science, University of Gujrat (2020). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including RLHF.

Labeling Experience

Senior LLM Trainer (Supervised Fine-Tuning and RLHF)

OtherRLHF

Conducted supervised fine-tuning of large language models (LLMs) and applied RLHF techniques to align model behavior with specific tasks and domains. Performed detailed evaluation of generated outputs using metrics such as BLEU scores and perplexity, followed by iterative optimization to improve robustness and generalization. Developed and maintained reusable training notebooks with documentation to enable reproducible training runs across experiments. • Supervised fine-tuning for task/domain alignment • RLHF-based refinement using user-feedback loops • Evaluation using BLEU and perplexity • Reproducible training notebooks and documentation

2024 - Present

Education

Work History