For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
Sanjay S

Sanjay S

LLM - Python Developer

INDIA flag
Erode, India
$8.00/hrIntermediateInternal Proprietary Tooling

Key Skills

Software

Internal/Proprietary Tooling

Top Subject Matter

No subject matter listed

Top Data Types

TextText

Top Label Types

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

Freelancer Overview

I am an AI and data science professional with hands-on experience in developing and optimizing LLM-based systems, focusing on data labeling, annotation, and AI training data workflows. My work includes designing RLHF and SFT pipelines, reducing LLM hallucinations through agentic workflows such as ReAct and Plan-and-Execute, and leading a team in LLM evaluation and benchmarking to enhance validation accuracy. I have a strong command of Python, SQL, and Power BI for analyzing both structured and unstructured datasets, and have built custom tools for structured outputs and autonomous task execution. My projects span multilingual speech-to-text pipelines and education-focused platforms, demonstrating my ability to deliver high-quality, production-ready solutions in NLP and AI domains. My background in prompt engineering, tool creation, and data-driven decision-making allows me to contribute effectively to any team focused on high-quality training data and annotation processes.

IntermediateEnglishTamil

Labeling Experience

LLM - Function Calling

Internal Proprietary ToolingTextRLHFFine Tuning
1. Designed and evaluated RL Gym–based agentic AI systems and databases using RLHF and SFT to continuously optimize LLM behavior and response quality. 2. Reduced LLM hallucinations by implementing agentic workflows with ReAct and Plan-and-Execute frameworks. 3. Built custom LLM tools using function calling to enable structured outputs, tool orchestration, and autonomous task execution. 4. Led a 6-member team in LLM evaluation and benchmarking, improving task validation accuracy.

1. Designed and evaluated RL Gym–based agentic AI systems and databases using RLHF and SFT to continuously optimize LLM behavior and response quality. 2. Reduced LLM hallucinations by implementing agentic workflows with ReAct and Plan-and-Execute frameworks. 3. Built custom LLM tools using function calling to enable structured outputs, tool orchestration, and autonomous task execution. 4. Led a 6-member team in LLM evaluation and benchmarking, improving task validation accuracy.

2024 - 2025

Education

R

Rathinam Technical Campus

Bachelor of Technology, Artificial Intelligence and Data Science

Bachelor of Technology
2021 - 2025
J

Jaycees Matriculation Higher Secondary School

Higher Secondary Certificate, Science

Higher Secondary Certificate
2021 - 2021

Work History

T

Turing

Python Developer

Palo Alto (Remote)
2024 - 2025
C

Codsoft

Data Science Intern

Coimbatore
2023 - 2023