Koushika K.

Key Skills

Software

Other

Top Subject Matter

LLM-based code evaluation and reasoning verification

LLM prompt engineering

response evaluation

Top Data Types

Text

Top Task Types

RLHF

Freelancer Overview

AI Interaction Evaluator (Codex / Claude Code) at DataAnnotation. 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 Technology in Computer Science, Shri Vishnu Engineering College For Women (2024). AI-training focus includes data types such as Computer Code and Programming and labeling workflows including Evaluation, Rating, and RLHF.

Labeling Experience

AI Interaction Evaluator - DataAnnotation

Computer Code ProgrammingRLHF

Worked with Codex and Claude Code CLI to evaluate AI-generated code, verify correctness, and analyze model rea soning across Python and software engineering tasks. Created test scenarios, identified failure cases, and provided structured feedback to improve AI model accuracy and coding performance.

2026 - 2026

AI Interaction Evaluator (Codex / Claude Code) at DataAnnotation

Evaluated AI-generated code and assessed correctness and reasoning quality across Python and software engineering tasks. Created test scenarios, identified failure cases, and provided structured feedback to improve model accuracy and coding performance. Built a structured data pipeline to reduce manual handling and streamline evaluation workflows. • Used Codex and Claude Code CLI to run and evaluate model outputs. • Verified code correctness and analyzed model reasoning. • Produced structured feedback for training/evaluation improvements. • Reduced manual handling by 60% through pipeline development.

2024 - 2026

Python Developer at Turing (Remote)

OtherRLHF

Worked on RLHF, supervised fine-tuning (SFT), and AI evaluation workflows for large language models. Designed and evaluated prompts involving Python programming to improve reasoning and coding behavior. Reviewed model responses for correctness, efficiency, maintainability, and adherence to project standards. • Participated in RLHF and SFT-oriented training pipelines. • Authored/evaluated prompts for Python programming tasks. • Performed response review against correctness and efficiency criteria. • Supported pipeline collaboration to enhance reasoning and coding capabilities.

2024 - 2025

Education

Work History