AI Model Evaluator

Strivanta | Remote (San Francisco, CA, USA)

Potpuno udaljeno Ugovor Ostalo
Prikaži izvorni popis (English) Pogledaj prijevod
Opis

As an AI Model Evaluator, you will review AI-generated responses and assess how accurate, relevant, and useful they are. Your judgment helps improve the quality of AI systems.

Employment type: Contract or Project-Based
Experience level: Intermediate
Location: Remote (US-based company headquartered in San Francisco, CA)
Compensation: Rates agreed before each assignment based on experience and project scope.

About Strivanta
Strivanta is a technology consulting and professional services company focused on software engineering, artificial intelligence, cloud solutions, technology staffing, and global professional talent services. We connect businesses with skilled technology professionals and subject matter experts through direct employment, project-based contracts, and client talent placement. Learn more at strivanta.dev. Connecting Global Talent with Technology and AI Opportunities.

How to apply
Apply here on WFHJ, or email your resume to admin@strivanta.dev with the job title in the subject line.

Strivanta is an equal opportunity employer. We welcome applicants of all backgrounds and consider every candidate on skills, experience, and qualifications, without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, veteran status, or any other protected characteristic.

Zahtjevi

- Intermediate experience in evaluation, research, editing, or a related field
- Strong analytical thinking
- Critical evaluation skills
- Strong writing skills
- Fact-checking ability
- Familiarity with AI tools

Nice to have:
- Experience in editing, research, or quality review
- Subject knowledge in a specific field
- Attention to detail on long, repetitive tasks
- Comfort working independently and remotely

Odgovornosti

- Evaluate AI-generated responses for accuracy and relevance
- Assess instruction following and overall response quality
- Fact-check claims and note errors or unsupported statements
- Write clear explanations for your ratings
- Compare responses and rank them against project criteria
- Apply evaluation guidelines consistently
- Provide feedback on guidelines and edge cases

Potrebne vještine

AI Evaluation, LLMs, Critical Thinking, Writing

Detalji posla

Iskustvo: 1 godine

Objavljeno: 2 days, 7 hours prije

Pogledi: 135

Prijavi se za primjenu
Dobiti prilagođenu aplikaciju za ovu ulogu

Bacite svoj životopis i mi ćemo napisati naslovno pismo usmjereno na ovaj točan popis - besplatno, i pripremite trenutak vaš račun je napravljen.

PDF, Riječ ili tekst. Sljedeći zaslon stvaramo vaš besplatni račun – bez kartice.

Zapošljavaš za ovakvu ulogu?

Pošaljite svoj udaljeni posao na WFHJ i dohvatite odgovarajuće kandidate. Bez naknada.

Pošaljite posao — besplatno
Feedback