Skip to main content
Rupa SinghRS
Open to opportunities

Rupa Singh

@rupasingh1

I tune LLMs through precise prompts, RLHF, and rigorous output evaluation.

Zimbabwe
Message

I've fine-tuned and evaluated AI model outputs across technical, creative, and business fields as an independent AI Training Specialist.

I build custom prompt templates and instruction sets for complex, multi-step LLM tasks, then score and correct outputs using RLHF principles to reduce hallucinations and improve factual accuracy. I also test edge cases and edge scenarios to uncover logical flaws and refine model performance.

Through contract and project work, I've designed domain-specific datasets for supervised fine-tuning and reviewed AI-generated text and visual prompts against strict formatting and style requirements.

I maintain prompt libraries that streamline content creation and repetitive workflows, drawing on machine learning concepts, advanced prompt design, and natural language processing.

Experience

Work history, roles, and key accomplishments

CP

Prompt Engineer & Quality Evaluator

Contract / Projects

Jan 2023 - Dec 2024 (1 year 11 months)

Designed domain-specific datasets used for supervised fine-tuning across different subject areas. Reviewed AI-generated text and visual prompts to ensure strict adherence to formatting and style rules.

Education

Degrees, certifications, and relevant coursework

Rupa hasn't added their education

Don't worry, there are 90k+ talented remote workers on Himalayas

Tech stack

Software and tools used professionally

Get matched with your dream remote job

Sign up now and join over 250,000+ remote workers who receive personalized job alerts, curated job matches, and more for free!

Sign up
Himalayas profile for an example user named Frankie Sullivan