For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
Sachin Mandpe

Sachin Mandpe

Python Data Scientist | LLM Trainer Specialist, Turing

India flagNagpur, India
$30.00/hrIntermediateMicro1MindriftScale AI

Key Skills

Software

Micro1
MindriftMindrift
Scale AIScale AI
Snorkel AISnorkel AI
SuperAnnotateSuperAnnotate

Top Subject Matter

LLM Evaluation
Nlp Domain Expertise
Code Generation

Top Data Types

TextText
DocumentDocument

Top Task Types

RLHF
Prompt Response Writing SFT

Freelancer Overview

Python Data Scientist | LLM Trainer Specialist, Turing. Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Docker. Education includes Bachelor of Engineering, SB Jain Institute of Technology Management and Research (2018). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including RLHF, Evaluation, and Rating.

IntermediateEnglishHindi

Labeling Experience

LLM Evaluation Specialist & Code Interpreter Auditor (Freelance), Revelo

At Revelo, I specialized in auditing LLM-generated Python tasks and designed structured multi-turn coding evaluations to assess agent reasoning. I verified unit tests, reference solutions, and evaluation rubrics for robustness and logical consistency. My responsibilities included benchmarking model performance for alignment improvements and identifying systematic coding gaps. • Audited 30+ Python tasks in Docker sandbox environments • Designed multi-turn coding evaluations and assessed agent reasoning • Benchmarked GPT-4 and Claude outputs for code alignment • Identified critical bugs, hardcoding, and reproducibility issues

At Revelo, I specialized in auditing LLM-generated Python tasks and designed structured multi-turn coding evaluations to assess agent reasoning. I verified unit tests, reference solutions, and evaluation rubrics for robustness and logical consistency. My responsibilities included benchmarking model performance for alignment improvements and identifying systematic coding gaps. • Audited 30+ Python tasks in Docker sandbox environments • Designed multi-turn coding evaluations and assessed agent reasoning • Benchmarked GPT-4 and Claude outputs for code alignment • Identified critical bugs, hardcoding, and reproducibility issues

2025 - Present

Python Data Scientist | LLM Trainer Specialist, Turing

TextRLHF
As an LLM Trainer Specialist at Turing, I executed RLHF evaluations on multi-turn reasoning and code-generation tasks for GPT-4 and Claude models. I maintained high-quality benchmarks through rubric-based scoring and continuous human-in-the-loop workflows. I also designed prompt templates and led structured error analysis to strengthen model alignment and output consistency. • Conducted 500+ RLHF evaluations across reasoning, NLP, and coding outputs • Built prompt frameworks improving response consistency by 25% • Automated evaluation workflows via Python and Docker pipelines • Validated RAG workflows and debugged LLM-generated code for correctness

As an LLM Trainer Specialist at Turing, I executed RLHF evaluations on multi-turn reasoning and code-generation tasks for GPT-4 and Claude models. I maintained high-quality benchmarks through rubric-based scoring and continuous human-in-the-loop workflows. I also designed prompt templates and led structured error analysis to strengthen model alignment and output consistency. • Conducted 500+ RLHF evaluations across reasoning, NLP, and coding outputs • Built prompt frameworks improving response consistency by 25% • Automated evaluation workflows via Python and Docker pipelines • Validated RAG workflows and debugged LLM-generated code for correctness

2023 - Present

Generalist AI Trainer (Freelance), Micro1

TextPrompt Response Writing SFT
As a Generalist AI Trainer at Micro1, I developed structured prompts and golden responses for LLM training workflows. I built chain-of-thought (CoT) evaluation rubrics and conducted reviews to improve model reasoning and output clarity. My systematic feedback helped reduce evaluation time and increase inter-annotator agreement. • Developed and refined LLM prompts and responses for training • Created CoT rubrics to benchmark LLM reasoning quality • Strengthened evaluation feedback loops for clarity and alignment • Achieved 20% reduction in evaluation time, with high inter-annotator agreement

As a Generalist AI Trainer at Micro1, I developed structured prompts and golden responses for LLM training workflows. I built chain-of-thought (CoT) evaluation rubrics and conducted reviews to improve model reasoning and output clarity. My systematic feedback helped reduce evaluation time and increase inter-annotator agreement. • Developed and refined LLM prompts and responses for training • Created CoT rubrics to benchmark LLM reasoning quality • Strengthened evaluation feedback loops for clarity and alignment • Achieved 20% reduction in evaluation time, with high inter-annotator agreement

2025 - 2025

Education

S

SB Jain Institute of Technology Management and Research

Bachelor of Engineering, Electronics and Telecommunications Engineering

Bachelor of Engineering
2014 - 2018

Work History

B

Byju’s

Pre-Sales Associate

Bengaluru
2021 - 2022
G

Gati Kwe

Associate – Supply Chain Operations

Nagpur
2019 - 2021