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

Tasks

• Automate eval pipeline execution at scale
• Build evaluation datasets and pipelines
• Build internal tools for error analysis and audits
• Design ontology and schema mappings
• Diagnose measurement path issues between offline evals and production
• Iterate on labeling frameworks and knowledge capture systems
• Monitor AI accuracy post launch
• Optimize prompts across full lifecycle
• Run prompt and model experiments

Perks/Benefits

• Family-friendly benefits
• Flexible schedule
• Hybrid work schedule
• Internal promotion opportunities

Skills/Tech-stack

Braintrust | LLM Accuracy | Langfuse | NumPy | Ontology | Pandas | Prompt engineering | Python | SQL | Schema Design