We are hiring Senior AI Evaluation & RLHF Specialists to work on advanced AI/LLM evaluation and alignment projects . The role involves evaluating AI-generated responses, preference ranking, RLHF data generation, multi-turn reasoning evaluation, and improving model outputs.
Key Responsibilities
- Evaluate and rank AI/LLM responses using detailed evaluation rubrics.
- Perform Side-by-Side (SxS) evaluations for factuality, helpfulness, safety, reasoning, coherence, and instruction-following.
- Identify errors and provide clear, fact-based evaluation rationales.
- Rewrite and improve AI-generated responses.
- Evaluate mathematical, logical, reasoning, and tool-use outputs.
- Review multi-turn conversations and agentic AI workflows.
- Create golden responses and edge-case examples.
- Participate in calibration sessions and maintain high inter-rater reliability.
- Follow evolving project guidelines and meet quality and productivity SLAs.
Required Skills
- 2+ years of hands-on experience in AI data annotation, AI model evaluation, RLHF, preference scoring, or AI training data.
- Experience working on complex AI/LLM evaluation projects.
- Solid analytical and critical-thinking skills.
- Excellent written English communication ( C1 or above ).
- Ability to provide objective, evidence-based evaluation rationales.
- Strong attention to detail and ability to follow complex guidelines.
- Comfortable working in a fast-paced, SLA-driven environment.