Mohammad Ali Ikram M.

Key Skills

Software

No software listed

Top Subject Matter

Large Language Models/Transformers

Software Engineering

Coding

Top Data Types

Text

Top Task Types

RLHF

Freelancer Overview

LLM Fine-tuning with RLHF (Pre-trained Model). Brings less than 1 year of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include PyTorch. Education includes Master of Computer Applications, Lovely Professional University (2024) and Bachelor of Computer Applications, Amity University (2022). AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

LLM Fine-tuning with RLHF (Pre-trained Model)

TextRLHF

I applied RLHF-style fine-tuning to a pre-trained transformer model, focusing on aligning outputs with human preferences. The process involved the training of a reward model using PyTorch and evaluating alignment improvements via response ranking and prompt-based testing. This work resulted in a 30% reduction in low-quality model responses, supporting improved AI alignment for deployment. • Conducted iterative RLHF fine-tuning cycles on LLM outputs • Trained reward models using human preference data • Evaluated model performance via ranking and prompt-response analysis • Used distributed clusters for scalable experimentation

2025 - 2026

Education

Work History