For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
Aman Roy

Aman Roy

LLM Labeling, RAG & Coding Eval Specialist | Fine-Tuning & STEM Expert

India flagSiliguri, India
$40.00/hrExpertAppenCrowdsourceData Annotation Tech

Key Skills

Software

AppenAppen
CrowdSourceCrowdSource
Data Annotation TechData Annotation Tech
DatasaurDatasaur
LabelboxLabelbox
LionbridgeLionbridge
MindriftMindrift
OneFormaOneForma
RemotasksRemotasks
Scale AIScale AI
Snorkel AISnorkel AI
SuperAnnotateSuperAnnotate
TolokaToloka
TelusTelus

Top Subject Matter

No subject matter listed

Top Data Types

Computer Code ProgrammingComputer Code Programming
ImageImage
TextText

Top Task Types

Computer Programming Coding
Evaluation Rating
Fine Tuning
Prompt Response Writing SFT
RLHF

Freelancer Overview

I bring over five years of experience as a full-stack software engineer with a strong foundation in data-driven projects, AI model evaluation, and large language model (LLM) training tasks. My work includes prompt rewriting, label refinement, and qualitative assessment of AI-generated content in both English and Spanish. I’ve contributed to key projects involving retrieval-augmented generation (RAG), coding assessments, and the fine-tuning of AI systems using supervised and reinforcement learning techniques. With a passion for STEM and a deep understanding of how AI systems learn, I aim to contribute meaningfully to the advancement of intelligent systems across diverse applications.

ExpertEnglishSpanish

Labeling Experience

Labelbox

Alignerr

LabelboxComputer Code ProgrammingRLHFFine Tuning
I contributed to AI training projects for Alignerr, focusing on multiple tasks across the data labeling lifecycle using Labelbox as the primary annotation tool. My responsibilities included Reinforcement Learning from Human Feedback (RLHF), fine-tuning support, and supervised fine-tuning (SFT), where I created high-quality prompt-response pairs to train large language models. I also performed LLM output evaluation and rating tasks to assess model alignment, coherence, and factual accuracy. The projects varied in size, from targeted batches to large-scale datasets involving thousands of samples. Additionally, I worked on evaluating and correcting computer programs—ensuring logic correctness, code quality, and adherence to best practices in languages like Java and Python. High accuracy and consistency were maintained through internal QA reviews, gold standard references, and clear labeling guidelines, ensuring the outputs met strict quality benchmarks set by the client.

I contributed to AI training projects for Alignerr, focusing on multiple tasks across the data labeling lifecycle using Labelbox as the primary annotation tool. My responsibilities included Reinforcement Learning from Human Feedback (RLHF), fine-tuning support, and supervised fine-tuning (SFT), where I created high-quality prompt-response pairs to train large language models. I also performed LLM output evaluation and rating tasks to assess model alignment, coherence, and factual accuracy. The projects varied in size, from targeted batches to large-scale datasets involving thousands of samples. Additionally, I worked on evaluating and correcting computer programs—ensuring logic correctness, code quality, and adherence to best practices in languages like Java and Python. High accuracy and consistency were maintained through internal QA reviews, gold standard references, and clear labeling guidelines, ensuring the outputs met strict quality benchmarks set by the client.

2024

Education

U

University Institute of Technology

Bachelor of Technology, Engineering

Bachelor of Technology
2015 - 2019
B

BSF Sr. Sec Residential School

Higher Secondary Education, Science

Higher Secondary Education
2013 - 2014

Work History

C

Comviva Technologies Ltd

Technical Lead

Bangalore
2023 - Present
T

Teksystems at Cisco

Software Engineer

Bangalore
2023