Mathematics Subject Matter Expert - AI Evaluation (UK-Remote)
Join to apply for the Mathematics Subject Matter Expert - AI Evaluation (UK-Remote) role at Braintrust
Seeking multiple Mathematics Subject Matter Experts to help design, run, and optimize data collection and evaluation workflows for GenAI research.
You’ll translate high-level research needs into scalable processes, produce and curate challenging domain problems, and ensure factual, bias‑aware, high‑quality datasets for LLM training.
* Immediate project need. Project approved for 3 months initially, with possibility to extend based on client demands.
* Fixed hourly rate project in USD ($75/hr)
Responsibilities
* Partner with GenAI researchers/engineers to capture data needs and success criteria.
* Expand high-level requirements into clear, executable workflows for larger teams.
* Execute collection/evaluation workflows rapidly with minimal supervision.
* Innovate on workflows to maximize throughput and quality.
* Collaborate cross-functionally to maintain quality at scale.
* Conduct in-depth LLM‑assisted research; gather reliable, up-to-date info.
* Craft original, high-quality content and hard problems for LLM eval/train.
* Perform rigorous fact‑checking (precision/recall) to prevent misinformation.
Requirements
* Education: Master’s with distinction or PhD in Mathematics; top‑tier institution preferred. Significant domain experience considered.
* Detail orientation; precise data presentation; thorough proofreading.
* Communication: articulate complex info; strong collaboration.
* Understanding of AI/LLMs, their capabilities/limits.
* Prompt engineering and familiarity with AI writing tools.
* Ethical AI awareness and data literacy (collection, cleaning, transformation).
* Thrives in fast‑paced, minimally supervised environments.
Seniority level
* Entry level
Employment type
* Full‑time
Job function
* Science and Research
Industries
* Higher Education and Education
Referrals increase your chances of interviewing at Braintrust by 2x
#J-18808-Ljbffr