Devansh S.

Key Skills

Software

Other

Top Subject Matter

LLM alignment

AI safety

RLHF-based training

Top Data Types

Text

Top Task Types

RLHF

Freelancer Overview

LLM Post-Training Intern (Remote) — Ethara AI. Brings 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, Accurate Institute of Management and Technology (2022) and Diploma in Mechanical Engineering, Lloyd Institute of Management & Technology (2022). AI-training focus includes data types such as Text and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

LLM Post-Training Intern (Remote) — Ethara AI

ImageRLHF

Performed LLM post-training evaluation by reviewing prompts for reasoning, summarization, and code-generation quality. Applied RLHF-based annotation techniques to improve model response behavior. Supported dataset validation and AI safety evaluation while identifying edge cases for fine-tuning decisions. • Labeled/improved prompt-response pairs using RLHF methodology • Performed structured reasoning and summarization quality checks • Identified edge cases to guide model fine-tuning • Collaborated on dataset validation and AI safety evaluation

2026 - 2026

Quality Analyst — PFEDA Synthetic Pvt. Ltd.

OtherText

Conducted quality inspections focused on documenting and improving production issues through structured evaluation. Applied analytical assessment practices to identify gaps and support corrective actions. Improved evaluation discipline that aligns with data-quality and labeling-style quality control expectations. • Performed quality inspections and documented production issues • Supported structured analysis to improve outcome quality • Helped identify problems for corrective action workflows • Strengthened analytical and evaluation skills

2022 - 2022

Education

Work History