Senior Software Engineer, Data Science
Core
Build evaluation infrastructure and tooling to measure and improve the accuracy of LLM-powered features that transform drone and robotics data into insights.
Role type
Senior Software Engineer (Data Science / AI Evaluation)
Builds
Data, tooling, and evaluation infrastructure for AI products
Domain
Construction technology / Industrial inspection / AI
Deliverable
production ML models
Required skills
Python, SQL, LLM evaluation, prompt engineering, data modeling, error analysis, ontology design
Preferred skills
Visual reasoning, labeling systems, construction domain knowledge
Technologies
pandas, NumPy, Braintrust, Langfuse
Responsibilities
Build and maintain robust dataset and evaluation infrastructure; Diagnose and fix measurement-path issues between offline evals and production accuracy; Own prompt optimization across its full lifecycle; Automate eval pipelines and build tooling to run them at scale; Create reusable internal tooling for error analysis, audits, and experimentation; Iterate on and scale existing labeling frameworks and knowledge capture systems.
Seniority
Senior, hands-on IC
