Skip to main content
Igor ChełchowskiIC
Looking for a job

Igor Chełchowski

@igorchechowski

I evaluate LLMs and agentic AI systems to improve model quality and reliability.

Poland
Message

At Keywords Studios / Sperasoft, contracted to support Amazon AI evaluation initiatives, I evaluate large language models and browser-based agentic AI systems through response ranking, preference comparisons, hallucination detection, fact-checking, and instruction-following assessments.

I've been promoted internally from AI Research Associate based on strong performance, quality, and consistent delivery above productivity targets. I create prompts and reasoning demonstrations, review model outputs, validate annotations supporting RLHF-related improvement, and assess chain-of-thought quality, tool use, and multi-step task completion.

Before AI research, I conducted functional QA testing for AAA games across PlayStation, Xbox, and PC, documenting and verifying defects in Jira. I'm credited in Call of Duty: Black Ops 6 and Call of Duty: Black Ops 7.

Experience

Work history, roles, and key accomplishments

KO
Current

AI Technical Research Associate

Keywords Studios / Sperasoft Poland Sp. z o.o.

Jul 2025 - Present (1 year 1 month)

Evaluated LLM and agentic AI systems through response ranking, preference comparisons, hallucination detection, fact-checking, and instruction-following assessments. Promoted internally based on strong performance and quality, and supported onboarding and documentation.

Education

Degrees, certifications, and relevant coursework

KW

Kadra Post-Secondary School, Wrocław

Diploma, Masseur Technician

2017 - 2019

Completed post-secondary education in massage therapy, gaining practical skills in the field.

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