[VMT] Platform AI Software Engineer
Core
Building the trust layer for an AI copilot that answers process engineers' questions about live plant data in oil refineries and chemical plants.
Role type
Senior IC Platform AI Software Engineer (LLM reliability & evaluation)
Builds
A natural-language interface for engineers to query live plant data with grounded, chart-backed answers.
Domain
Industrial process engineering (oil refineries, chemical plants) + Large Language Models
Deliverable
production ML models | product features
Required skills
Python (large shared codebases), LLM-based feature production, production debugging (latency/concurrency), prompt engineering as code, feature-flag discipline, high autonomy
Preferred skills
GCP (Vertex AI), observability tooling, charting/plotting pipelines, industrial/time-series data domain, heavy AI-tooling workflows
Technologies
Python, GCP, Vertex AI, AWS, Azure, matplotlib
Responsibilities
Investigate agent misbehavior from customer plants and implement fixes with regression tests; Build and extend evaluation harnesses for prompt changes and model migrations; Add reliability mechanisms (assumption surfacing, grounding checks, output-quality reviewers); Diagnose and resolve cross-cutting performance and concurrency issues
Seniority
Senior, hands-on IC