Looking for a job

Srin Srinivas

@srinsrinivas

Message

I evaluate LLM outputs, detect hallucinations, and engineer prompts to improve AI accuracy and reasoning.

India

Message

What I'm looking for

I'm looking for a Prompt Engineer or LLM Evaluator role where I can apply RLHF evaluation, hallucination detection, structured feedback, and prompt testing to improve model reasoning, accuracy, and safety.

I've evaluated LLM outputs at Innodata for accuracy, reasoning, quality, and safety using structured rubrics and rating scales.

I conduct side-by-side response comparisons, identify hallucinations and factual inconsistencies, and write clear rationales that support RLHF-aligned model improvement.

I've designed and refined prompts to stress-test model reasoning, surface edge cases, and improve response quality across text, image, and audio outputs.

Previously at NVIDIA, I performed large-scale annotation and quality audits for NLP, computer vision, and speech-recognition training datasets across text, image, and video projects.

Experience

Work history, roles, and key accomplishments

AI/LLM Analyst

Innodata

Dec 2025 - Jun 2026 (6 months)

Evaluated LLM outputs for accuracy, reasoning, and quality using structured rubrics and rating scales. Performed SxS comparisons, identified hallucinations, and applied RLHF-aligned evaluation practices.

LLM Evaluation RLHF SxS Comparison Hallucination Detection Prompt Engineering Data Annotation Quality Assurance