For employers

Hire this AI Trainer

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

Invite to Job
D
Divyansh T.

Divyansh T.

LLM Personalization Specialist at Turing — RLHF and quality evaluation for Tier-1 LLM projects.

India flagN/A, India

Key Skills

Software

No software listed

Top Subject Matter

RLHF and quality evaluation for large language models (Google Gemini).
UI/UX design for product experiences (supporting AI experience evaluation and presentation).

Top Data Types

TextText

Top Task Types

RLHFRLHF
Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)

Freelancer Overview

LLM Personalization Specialist at Turing — RLHF and quality evaluation for Tier-1 LLM projects.. Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Figma. Education includes Bachelor of Technology, Dr. A.P.J. Abdul Kalam Technical University (2022). AI-training focus includes data types such as Text and labeling workflows including RLHF and Prompt + Response Writing (SFT).

Labeling Experience

LLM Personalization Specialist (RLHF & Quality Evaluation) - Turing

TextTextRLHFRLHF

You specialize in reinforcement learning from human feedback and quality evaluation for Tier-1 LLM projects, with a focus on ensuring language accuracy and contextual relevance. You evaluate LLM responses and collaborate with cross-functional teams to refine prompt design and personalization strategies. The role requires strong problem-solving skills, prompt engineering knowledge, and familiarity with AI model evaluation workflows. • Evaluate large language model outputs for language accuracy and contextual relevance • Refine prompt design and personalization strategies with cross-functional teams • Improve model output quality and track user engagement metrics • Support RLHF and quality assurance processes for production LLM systems

2026 - Present

LLM Personalization Specialist at Turing — RLHF and quality evaluation for Tier-1 LLM projects.

TextTextRLHFRLHF

Evaluate and assess Tier-1 LLM responses to support RLHF-driven quality improvements for Google Gemini projects. Apply judgment on language accuracy and contextual relevance as part of the model improvement loop. Collaborate on prompt design and personalization strategies to improve output quality and user engagement. • Review LLM response quality against language and context criteria. • Refine personalization prompts and strategies with cross-functional teams. • Perform quality evaluation to guide RLHF-style training and tuning. • Use problem-solving to increase response quality metrics.

2026 - Present

Freelance designer — UI/UX design and product design (supporting AI experience presentation).

TextTextPrompt + Response Writing (SFT)Prompt + Response Writing (SFT)

Create product UI/UX content and interactive design assets to support AI-related user experiences, including user journey and flow artifacts that guide how responses should be presented. Translate design requirements into structured screens and interaction states. Use these artifacts to improve usability and alignment of AI-driven experiences. • Design UI/UX layouts and user journey maps in Figma. • Build wireframes and high-fidelity prototypes to support interaction design. • Produce accessible UI flows for key user operations. • Prepare visual assets and brand elements to support user engagement.

2024 - Present

Education

D

Dr. A.P.J. Abdul Kalam Technical University

Bachelor of Technology, Electronics and Communication Engineering

Bachelor of Technology
2022

Work History

T

Turing

LLM Personalization Specialist (RLHF & Quality Evaluation)

N/A
2026 - Present
F

Freelance

Freelance Product Designer & 3D Artist

N/A
2024 - Present