
AI Data Evaluation Senior Specialist (RLHF & SFT)
Szczecin
Wigi highlights
21+ years, currently working as AI Evaluation Senior Specialist
Design prompts and adversarial tests to evaluate model safety
Deploy local testing environments on dedicated RTX hardware
In the current role, they conduct rigorous quality audits of LLM outputs across creative, coding and logical reasoning domains, evaluating instruction-following, truthfulness (hallucinations), logic and formatting compliance. Drafting and optimizing multi-dimensional grading rubrics and evaluation guidelines ensures consistent high-quality human-feedback loops.
Separate responsibilities include evaluating and labeling high-volume multimedia (text, audio, video) under User-Generated Content (UGC) safety policies to flag hate speech, cyberbullying and dangerous activities. They also audit model responses to potentially toxic or harmful prompts, ensuring strict adherence to safety guidelines and preventing unsafe outputs. General capabilities include Information Security Policy, Natural Language and Neural Networks.
Available in 2 weeks
Ready to start in 2 weeks. Interview now. Actively looking.
Skills
Work experience
Unlocks when they connect with you.
- certifications· 4
- education· 1
Similar available Generative AI & LLM Engineers
View all- AI Platform Engineer | Vector Search & Enterprise Search · Lahore, Pakistan · 4 Yrs Exp · Remote, Hybrid, On-site · $2,500/mo
- Snowflake Data Scientist (Python (Programming Language)) · Lviv, Ukraine · 3 Yrs Exp · On-site · $3,000/mo
- Director of Generative AI and LLMs (LlamaIndex, Design Thinking) · London, UK · 10+ Yrs Exp · Hybrid · $12,600/mo
- AI Content Generation Specialist (SQL, Flask) · Hamburg, Germany · 10+ Yrs Exp · Hybrid · $5,200/mo
- Generative AI Engineer, Human-Centered AI Fluency · Port Saint Lucie, FL · 5 Yrs Exp · Remote · $11,800/mo