Open to opportunities

Naveed Shaik

@naveedshaik

Message

I build evaluation frameworks and high-quality data pipelines for LLM training.

India

Message

What I'm looking for

I'm looking for opportunities to evaluate and improve LLMs through RLHF, prompt testing, data annotation, and performance analysis, collaborating with AI and machine learning teams on high-quality training data.

I've built LLM evaluation frameworks at Remotasks/Scale AI, testing summarization, reasoning, and dialogue outputs through Python-based automated pipelines. I worked with ML engineers to track factual accuracy and helpfulness metrics that support model refinement.

Across Scale AI and Telus International, I've contributed to RLHF prompt-response assessments, structured prompt testing, web-scraped image validation, and annotation for image and video datasets. I labeled 500+ videos in CVAT for engagement-bait detection and annotated mathematical formula images for object-detection datasets.

I also bring experience in legal affairs, legal research, regulatory compliance, financial audits, and documentation. I enjoy turning unstructured data into reliable inputs for intelligent systems through careful evaluation and actionable feedback.

Experience

Work history, roles, and key accomplishments

LLM Evaluator & RLHF Expert

Remotasks / Scale AI

Designed and implemented test frameworks to evaluate LLM performance across summarization, reasoning, and dialogue tasks. Built Python-based automated pipelines to streamline LLM output evaluation and increase testing efficiency.

LLM Evaluation RLHF Python Testing Frameworks Data Annotation Performance Metrics