Senior Data Science Engineer – Eval Pipelines & LLM Prompts

Jobtailor seeks a Python-driven data professional to build and maintain evaluation datasets and tooling, ensuring robust ground-truth quality and scalable label systems. You will own prompt optimization from selection to deployment, while diagnosing issues between offline evals and production accuracy across multiple AI products.

Ideal candidates know Python (pandas, NumPy), SQL, and data science foundations for LLM accuracy, plus hands-on experience with Braintrust or Langfuse for evaluation