Lead NLP / ML Researcher (LLM Evaluation & Agentic Systems)
Summary
Lead NLP/ML researcher role at Irisai working remotely on LLM evaluation and agentic systems. The person leads research on model interpretability, RAG evaluation, benchmarking, and uncertainty methods, publishes papers, co-authors grants, and translates research into production prototypes.
- Analyze model interpretability and mechanisms
- Build RAG and indexing evaluation approaches
- Collaborate with engineering and product teams
- Conduct benchmarking and ablation studies
- Design uncertainty and confidence methods
- Develop evaluation metrics and frameworks
- Lead LLM evaluation research
- Lead and co author research grant proposals
- Publish research articles
- Translate research into prototypes and production capabilities
Perks/Benefits:
- Equipment budget
- Flexible hours
- Health checks
- Knowledge sharing
- Learning and development days
- Learning budget
- Mentorship
- Paid vacation
- Pair-coding
- Private health insurance
- Remote-first
- Team retreats