About the role
Procore is seeking a Senior Software Engineer for its Data Science team in Auckland. You will own the accuracy of LLM-powered features, build data, tooling, and evaluation infra, and raise AI product quality across platforms.
You’ll work with engineering, product, and AI teams to manage data pipelines, ground-truthing, and prompt lifecycle optimization, with a focus on measurable improvements in model performance. Occasional travel and hybrid office expectations apply.
Build and maintain robust dataset and evaluation infrastructure, including ground-truth quality controls. Diagnose and fix measurement-path issues between offline evals and production accuracy. Own prompt optimization across its full lifecycle, from candidate selection through production rollout and post-launch validation. Automate eval pipelines and build tooling to run them at scale across multiple AI products. Create reusable internal tooling for error analysis, audits, and experimentation. Iterate on and scale existing labeling frameworks and knowledge capture systems. Analyze how changes to ontology and schema propagate across models and infrastructure. Prioritize work by likely impact. Strong Python for data manipulation, analysis, and tooling. Solid SQL and database experience with large datasets. Data science background with knowledge of LLM accuracy. Experience building evaluation datasets and debugging evals with Braintrust or Langfuse. Experience designing ground-truth and labeling systems. Familiarity with prompt engineering and ontology/schema design. Collaborative, ownership-driven mindset. Construction or industrial inspection domain knowledge is a plus. Equity compensation Bonus incentive