About this role
AI Evaluation Scientist at Steampunk. Location: McLean, Virginia, United States. Role: implementing evaluation, building pipelines, conducting audits Requirements: Design and run AI evaluation frameworks, build automated tests and benchmarks, perform LLM/RAG audits, and map findings to responsible AI principles; requires advanced AI evaluation experience and programming proficiency. Category: Research and Development (R&D) Seniority: Senior Level Tools: Python, PyTorch, Hugging Face, scikit-learn, LangChain, Ragas Certifications: nist ai rmf (aisic), informs cap, aws ml, azure ml, google ml Commitment: Full Time Workplace: Onsite Languages: English