For employers

Hire this AI Trainer

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

Invite to Job
Pawan Agrahri

Pawan Agrahri

AI Engineer and Senior Auditor (Oracle Tier) at Outlier

INDIA flag
Lucknow, India
$25.00/hrExpertOtherAppenCrowdsource

Key Skills

Software

Other
AppenAppen
CrowdSourceCrowdSource
Data Annotation TechData Annotation Tech
LabelboxLabelbox
Scale AIScale AI
AWS SageMakerAWS SageMaker
Axiom AI
ClickworkerClickworker
Google Cloud Vertex AIGoogle Cloud Vertex AI
Label StudioLabel Studio
MercorMercor
Micro1
Redbrick AIRedbrick AI
Snorkel AISnorkel AI

Top Subject Matter

Mathematics Domain Expertise
Programming Domain Expertise
LLM Alignment

Top Data Types

TextText
DocumentDocument
Computer Code ProgrammingComputer Code Programming

Top Task Types

RLHF
Prompt Response Writing SFT
Computer Programming Coding
Data Collection
Function Calling
Evaluation Rating
Segmentation

Freelancer Overview

AI Engineer and Senior Auditor (Oracle Tier) at Outlier. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Master of Arts, Allahabad State University (2022) and Bachelor of Technology, JSS Academy of Technology (2019). AI-training focus includes data types such as Text and labeling workflows including RLHF.

ExpertHindiArabicBurmeseEnglish

Labeling Experience

AI Engineer and Senior Auditor (Oracle Tier) at Outlier

OtherTextRLHF
I am engaged as an AI Engineer focusing on LLM training and Reinforcement Learning from Human Feedback (RLHF) at Outlier. My responsibilities include evaluating, rating, and correcting code and mathematical responses to improve model accuracy. I ensure model outputs are aligned with quality standards and subject-matter expectations. • Conduct RLHF labeling on mathematical and programming responses • Audit and correct outputs for alignment and high fidelity • Collaborate with teams to deliver over 100 RLHF and evaluation projects • Leverage analytical skills in text and code evaluation

I am engaged as an AI Engineer focusing on LLM training and Reinforcement Learning from Human Feedback (RLHF) at Outlier. My responsibilities include evaluating, rating, and correcting code and mathematical responses to improve model accuracy. I ensure model outputs are aligned with quality standards and subject-matter expectations. • Conduct RLHF labeling on mathematical and programming responses • Audit and correct outputs for alignment and high fidelity • Collaborate with teams to deliver over 100 RLHF and evaluation projects • Leverage analytical skills in text and code evaluation

2024 - Present

Education

N

NIT Delhi

M.Tech, Ai and Machine learning

M.Tech
2022 - 2024
A

Allahabad State University

Master of Arts, Geography

Master of Arts
2020 - 2022

Work History

S

Scale Ai

Oracle Coder

new york
2023 - 2025
Z

Zenith

Senior Business Teacher

Lucknow
2021 - 2023