Lukman Hakim
@lukmanhakim
I evaluate and improve LLM responses through RLHF, safety review, localization, and QA testing.
IndonesiaWhat I'm looking for
I've evaluated and ranked multi-turn AI responses across Outlier/Remotasks, Scale AI, Appen, TELUS, Alignerr, Toloka, Clickworker, and Welocalize since 2021. My work covers factuality, reasoning, tone, and safety-policy compliance, with approximately 90% QA agreement.
I've completed RLHF preference-pairing, prompt-response rating, and live Speech-to-Speech evaluation work. I also reviewed user-generated content for violence, hate speech, spam, and adult-content policy violations on CrowdGen's Ogden project.
I bring Indonesian and Malay localization review, structured JSON and database logic awareness, and web QA testing experience. I document UI defects, workflow anomalies, reproduction steps, and diagnostic evidence to support faster developer triage.
Experience
Work history, roles, and key accomplishments
AI Data Annotator & LLM Response Evaluator
Freelance / Multi-Platform
Jan 2021 - Present (5 years 8 months)
Evaluated and ranked AI-generated multi-turn responses for factual accuracy, reasoning logic, tone alignment, and safety-policy compliance, maintaining a ~90% QA agreement rate. Executed RLHF preference-comparison and prompt-response rating tasks across 8+ crowdsourcing platforms.
Education
Degrees, certifications, and relevant coursework
Mercu Buana University
Bachelor of Science, Information Systems
2008 - 2012
Bachelor of Science in Information Systems (S.Kom) with coursework focus on enterprise system analysis, database logic, and data verification frameworks.
Availability
Location
IndonesiaAuthorized to work in
Salary expectations
Social media
Skills
Interested in hiring Lukman?
You can contact Lukman and 90k+ other talented remote workers on Himalayas.
Message LukmanGet 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!
