Open to opportunities

Suraj User

@surajuser7

Message

AI-driven analyst specializing in LLM evaluation, prompt engineering, and model failure-mode analysis.

India

Message

What I'm looking for

I seek roles focused on LLM evaluation, prompt engineering, or AI quality that emphasize rigorous evaluation, documentation, and opportunities to improve model reliability.

I am an AI-driven analyst focused on LLM evaluation, prompt engineering, and model behaviour assessment, combining structured evaluation practices with clear documentation workflows.

My hands-on experience includes identifying prompt-level failure modes such as ambiguity, assumption injection, instruction-following drift and hallucinations, and supporting prompt optimization to improve model reliability.

I also bring financial analytics experience—financial modeling, equity and technical analysis, and dashboarding—and I am currently pursuing Advanced AI & Emerging Technologies at IIT Hyderabad.

Experience

Work history, roles, and key accomplishments

AI Model Trainer

Outlier.ai

Aug 2024 - Nov 2024 (3 months)

Evaluated LLM outputs for reasoning quality and instruction adherence, identified hallucination and ambiguity failure patterns, and supported prompt optimization to improve model reliability over a 4-month engagement.

Prompt Engineering LLM Prompts Optimization Data Annotation Notion

Membership & Inspection Intern

ICCL

Mar 2023 - May 2023 (2 months)

Streamlined onboarding and compliance documentation, designed collateral optimization logic to reduce segment shortfall risk, and supported SEBI regulatory data queries during a 3-month internship.

Compliance Process Improvement Regulatory Data Analysis SEBI Excel

Financial Research Intern

Jamnadas Virji Advisory

Jun 2022 - Sep 2022 (3 months)

Built DCF valuation models for 10 listed companies, conducted Auto & Metals sector research, and performed technical analysis on BSE 500 stocks across a 4-month internship.

Valuation Equity Research Sectors Excel Financial Modeling BSE