Senior Software Engineer, Data Science (AI Accuracy) (NZ)

📋 Description

• Build and maintain dataset and evaluation infrastructure, incl. ground-truth controls
• Diagnose and fix measurement-path issues between offline evals and production accuracy
• Iterate on and scale labeling frameworks and knowledge capture systems
• Own prompt optimization across lifecycle: selection to deployment and validation
• Automate eval pipelines and tooling to run at scale across AI products
• Create reusable tooling for error analysis, audits, and experimentation; prioritize impact

🎯 Requirements

• Strong Python experience for data manipulation, analysis, tooling (pandas, NumPy)
• Solid SQL and database experience: querying, modeling, large datasets
• Data science background with LLM accuracy and visual reasoning
• Build evaluation datasets; run/debug evals with Braintrust or Langfuse; error analysis
• Design ground-truth and labeling systems; measure label agreement and data quality
• Familiar with prompt engineering across full lifecycle: selection to deployment

🎁 Benefits

• Mostly remote-first culture with flexible schedules
• Family-friendly benefits and strong internal promotions
• Growth opportunities and personal development
• Work with cutting-edge AI and robotics