Madhu

Key Skills

Software

Other

Top Subject Matter

LLM training and coding assistance

Data engineering for structured dataset preparation

Top Data Types

Text

Top Task Types

Prompt + Response Writing (SFT)

Entity (NER) Classification

Freelancer Overview

AI Trainer / Coding Expert (Outlier.ai, Remote). Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Bachelor of Engineering, JSS Academy of Technical Education (2019) and Higher Secondary Certificate, Expert PU Science College (2015). AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including Prompt + Response Writing (SFT), Evaluation, and Rating.

Labeling Experience

AI Trainer / Coding Expert - Outlier.ai

TextEntity (NER) Classification

As an AI Trainer and Coding Expert, you trained and evaluated model outputs for coding-focused projects and improved prompt effectiveness. You designed datasets and evaluation rubrics to support imitation learning and reward-modeling-style feedback pipelines. You also contributed to reinforcement learning work by implementing rewards and validating agent behavior through iterative testing. • Trained and evaluated LLM outputs across multiple coding-focused projects • Engineered imitation learning trajectory datasets and prompt strategies • Designed evaluation rubrics and unit tests to gate output correctness and safety • Built reinforcement learning components for reward functions, state representations, and training environments

2024 - Present

AI Trainer / Coding Expert (Outlier.ai, Remote)

Prompt + Response Writing (SFT)

Trained and evaluated LLM outputs across multiple coding-focused projects by designing prompts with domain coverage and safety constraints to improve accuracy and robustness. Engineered imitation-learning demonstration datasets and authored evaluation rubrics with weighted scoring to act as a structured proxy for reward modeling in RLHF-style pipelines. Implemented unit tests to gate AI-generated outputs for correctness, formatting validity, and safety before downstream evaluation. • Trained/evaluated LLM outputs for 5-6 coding projects. • Designed prompts for multi-domain behavior, safety constraints, and cross-platform output handling. • Built silver trajectory datasets for imitation learning. • Created unit tests and evaluation rubrics for reward-model-like scoring.

2024 - Present

Data Engineer Trainee (ITTStar Global Services Pvt Ltd)

Other

Supported AI/data work by building Python-based data transformation and cleaning pipelines to prepare structured datasets for downstream analytics workflows. Applied DevOps practices such as CI/CD and containerization to create reliable, repeatable data workflows used in model/data development contexts. Contributed hands-on AWS expertise across core services while developing and maintaining processing pipelines. • Built data transformation and cleaning pipelines using Python and Pandas. • Implemented CI/CD principles and containerization for repeatable workflows. • Processed structured datasets to support downstream analytics workflows. • Developed AWS service knowledge for data processing automation.

2023 - 2024

Education

Work History