Kedar Chinchanikar

Key Skills

Software

Mercor

OpenCV AI Kit (OAK)

Surge AI

Appen

Labelbox

Scale AI

Top Subject Matter

LLM output evaluation

Rlhf Domain Expertise

supervised fine-tuning

Top Data Types

Video

Image

Audio

Text

Top Task Types

Evaluation/Rating

RLHF

Fine-tuning

Classification

Segmentation

Object Detection

Text Summarization

Question Answering

Text Generation

Computer Programming/Coding

Freelancer Overview

AI Trainer / Data Annotator. Core strengths include Labelbox, Scale AI, and Appen. Education includes Diploma in Filmmaking, Film Institute. AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

Java Code Specialist – AI Trainer

As a Java Code Specialist – AI Trainer at Meridial by Invisible, I focused on improving the quality of AI-generated code. My main responsibilities included evaluating and providing structured feedback on Java code produced by AI systems. I ensured correctness, performance, and maintainability while applying best coding practices. • Reviewed AI-generated Java code to identify bugs, edge cases, and performance issues. • Provided detailed feedback to improve AI code output using clean code and debugging best practices. • Enhanced AI training effectiveness by systematically evaluating code samples and outputs. • Collaborated in developing high-quality datasets for AI coding models through thorough code assessments.

As a Java Code Specialist – AI Trainer at Meridial by Invisible, I focused on improving the quality of AI-generated code. My main responsibilities included evaluating and providing structured feedback on Java code produced by AI systems. I ensured correctness, performance, and maintainability while applying best coding practices. • Reviewed AI-generated Java code to identify bugs, edge cases, and performance issues. • Provided detailed feedback to improve AI code output using clean code and debugging best practices. • Enhanced AI training effectiveness by systematically evaluating code samples and outputs. • Collaborated in developing high-quality datasets for AI coding models through thorough code assessments.

2026 - Present

AI Trainer / LLM Evaluator – Meridian

LabelboxTextRLHF

As an AI Trainer at Meridian, I evaluated large language model outputs for factuality, coherence, instruction-following, tone, and safety. I authored prompt-response preference pairs assisting RLHF and supervised fine-tuning pipelines. My responsibilities included identifying model hallucinations, logical inconsistencies, and edge-case failures while maintaining a high annotation consistency rate. • Developed and applied scoring rubrics to assess responses across multiple dimensions. • Contributed to red-teaming exercises and tested model robustness with adversarial prompts. • Collaborated with QA leads to refine labeling standards and onboarding processes. • Utilized industry-standard platforms to accomplish high-volume annotation workflows.

As an AI Trainer at Meridian, I evaluated large language model outputs for factuality, coherence, instruction-following, tone, and safety. I authored prompt-response preference pairs assisting RLHF and supervised fine-tuning pipelines. My responsibilities included identifying model hallucinations, logical inconsistencies, and edge-case failures while maintaining a high annotation consistency rate. • Developed and applied scoring rubrics to assess responses across multiple dimensions. • Contributed to red-teaming exercises and tested model robustness with adversarial prompts. • Collaborated with QA leads to refine labeling standards and onboarding processes. • Utilized industry-standard platforms to accomplish high-volume annotation workflows.

2024 - Present

Education

Work History