For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
M
Mohan Raghu

Mohan Raghu

AI/ML Analyst – LLM Evaluation and RLHF Assessment

India flagKHAMMAМ, India
$10.00/hrIntermediateGoogle Cloud Vertex AIOneformaMercor

Key Skills

Software

Google Cloud Vertex AIGoogle Cloud Vertex AI
OneFormaOneForma
MercorMercor
RemotasksRemotasks

Top Subject Matter

Large Language Models (LLMs)
AI Evaluation
Nlp Domain Expertise

Top Data Types

TextText
ImageImage
DocumentDocument

Top Task Types

RLHFRLHF
ClassificationClassification

Freelancer Overview

AI/ML Analyst – LLM Evaluation and RLHF Assessment. Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Technology, N/A (2019). AI-training focus includes data types such as Text and labeling workflows including RLHF, Evaluation, and Rating.

IntermediateEnglishHindiTelugu

Labeling Experience

AI/ML Analyst – LLM Evaluation and RLHF Assessment

TextRLHF
As an AI/ML Analyst at Innodata (Client: Meta), I evaluated large language model (LLM) responses using reinforcement learning from human feedback (RLHF) methodologies. My responsibilities included daily assessment of over 500 LLM outputs for quality, policy compliance, and adherence to guidelines. I contributed to enhancing AI safety and reliability through comprehensive QA and hallucination detection processes. • Performed RLHF-based evaluation and response ranking of LLM outputs. • Ensured policy compliance, factuality, and helpfulness through justification writing. • Identified and documented model hallucinations and edge cases. • Maintained strict SOP and dataset confidentiality protocols.

As an AI/ML Analyst at Innodata (Client: Meta), I evaluated large language model (LLM) responses using reinforcement learning from human feedback (RLHF) methodologies. My responsibilities included daily assessment of over 500 LLM outputs for quality, policy compliance, and adherence to guidelines. I contributed to enhancing AI safety and reliability through comprehensive QA and hallucination detection processes. • Performed RLHF-based evaluation and response ranking of LLM outputs. • Ensured policy compliance, factuality, and helpfulness through justification writing. • Identified and documented model hallucinations and edge cases. • Maintained strict SOP and dataset confidentiality protocols.

2025 - Present

AI/ML Associate – Annotation and Output Validation

Text
During my role as an AI/ML Associate at Amazon, I supported model training through large-scale annotation and validation. I meticulously reviewed AI-generated outputs for accuracy and compliance with established guidelines. Quality benchmarks and annotation consistency were continually improved through my contributions. • Conducted text annotation and model output validation at scale. • Reviewed and rated AI outputs for accuracy and consistency. • Escalated edge cases and participated in annotation QA processes. • Helped refine annotation protocols to meet higher quality standards.

During my role as an AI/ML Associate at Amazon, I supported model training through large-scale annotation and validation. I meticulously reviewed AI-generated outputs for accuracy and compliance with established guidelines. Quality benchmarks and annotation consistency were continually improved through my contributions. • Conducted text annotation and model output validation at scale. • Reviewed and rated AI outputs for accuracy and consistency. • Escalated edge cases and participated in annotation QA processes. • Helped refine annotation protocols to meet higher quality standards.

2023 - 2024

Associate – Data Annotation and Classification

TextClassification
As an Associate at Wipro (Client: Google), I performed data annotation and labeling for machine learning datasets across several domains. My work involved detailed guideline-based classification and supported the preparation of quality training data for AI pipelines. I contributed significantly to the accuracy and efficiency of end-to-end ML projects. • Executed text data annotation and label classification tasks. • Performed extensive dataset preparation for ML pipelines. • Implemented strict quality checks per project guidelines. • Ensured high annotation productivity and data consistency.

As an Associate at Wipro (Client: Google), I performed data annotation and labeling for machine learning datasets across several domains. My work involved detailed guideline-based classification and supported the preparation of quality training data for AI pipelines. I contributed significantly to the accuracy and efficiency of end-to-end ML projects. • Executed text data annotation and label classification tasks. • Performed extensive dataset preparation for ML pipelines. • Implemented strict quality checks per project guidelines. • Ensured high annotation productivity and data consistency.

2022 - 2023

Education

N

N/A

Bachelor of Technology, Electronics and Communication Engineering

Bachelor of Technology
2019 - 2019

Work History

A

AI/ML Analyst (Client: Meta) (

Innodata

Location not specified
2025 - Present
A

AI/ML Associate (Client: Amazon) (

Amazon

Location not specified
2023 - 2024