{"$schema":"https://raw.githubusercontent.com/jsonresume/resume-schema/v1.0.0/schema.json","basics":{"name":"Matt Kerkstra","label":"Staff AI Engineer","email":"mattkerkstra@gmail.com","phone":"918-398-3588","url":"https://www.kerkstra.dev","summary":"Staff-level AI engineer with seven years building customer-facing production systems. At VideaHealth, I operate at Staff scope across 45 engineers, owning LLM product delivery from evaluation and retrieval through KServe/vLLM serving, Kubernetes operations, backend integrations, safe rollout, and user feedback. Cut clinician edit rate from roughly 60% to 40%, shipped production AI in 16 days, and enable six engineers across 13 namespaces and nine services. TypeScript, Python, Go, React, PostgreSQL.","location":{"city":"Austin","region":"TX","countryCode":"US"},"profiles":[{"network":"GitHub","username":"mkerkstra","url":"https://github.com/mkerkstra"},{"network":"LinkedIn","username":"matt-kerkstra","url":"https://linkedin.com/in/matt-kerkstra"}]},"work":[{"name":"VideaHealth","position":"Senior Software Engineer","url":"https://www.videahealth.com/","startDate":"2023-05-01","summary":"Operating at Staff scope across a 45-person engineering org: own production LLM products, the Kubernetes ML platform, and source-system integrations.","highlights":["Co-led AI product delivery for Canon, replacing fixed clinical-note templates with a block-based system that learns each customer's structure from examples. Built the evaluation and evidence-gated rollout around deterministic diffs, LLM-as-judge over semantic differences, and clinician calibration. Cutover proceeded customer by customer, and clinician edit rate per section fell from roughly 60% to 40%.","Shipped the first production clinical-note LLM system with two teammates in 16 days across 3 services: graph-based orchestration with Postgres checkpointing, BAAI/bge-m3 embeddings + Milvus retrieval, dual-detector PHI anonymization (Presidio + LLM), SSE streaming, and an admin review UI. Onboarding shipped as an agent skill for iteration speed, with the hardening plan written down up front.","Built the AI evaluation and feedback loop with the voice and product teams: clinician edits attributed to the block that produced the text, per-block performance statistics, and edit-pattern dashboards. Turned prioritization debates into measured user behavior and gave clinicians the deciding vote on what ships next.","Own the Kubernetes ML platform the org deploys on: Istio ambient mesh, ArgoCD app-of-apps with Kustomize overlays, KServe + vLLM self-hosted model serving (embeddings, ASR), Langfuse for LLM observability, Milvus for vector search - 13 namespaces / 9 services. Built with the platform team; new services ship with a Helm chart and an ArgoCD app, cost stayed flat, and six engineers contribute regularly.","Designed a production shadow evaluation with the voice team: both diarization variants generated on sampled real sessions, the delivered note never waits, and go-live is a reviewer-gated config change. The design answers \"does speaker attribution improve the output?\" with production traffic and zero patient-facing exposure.","Led the MongoDB → PostgreSQL/PostGIS migration of 100M+ clinical analysis records with the data and CV teams; heavy queries dropped from >5s to <500ms. Own the chain from schemas through Python treatment-recommendation algorithms to TypeScript integrations across 10+ versions.","Built the end-to-end voice-to-clinical-note product: offline-resilient React/browser capture, BullMQ async processing, transcription, structured LLM summarization, and practice-management-system context. More than 60K TypeScript LOC across client and API.","Delivered the unified-appointments backend behind the largest dental services organization (DSO) contract in the United States - vault practice search, dual-mode practice support, legacy PMS integration optimizations.","Run the bi-weekly Backend Guild (18+ months): typed query patterns (Kysely + footgun-prevention bots) adopted org-wide, AI-assisted developer tooling, architecture decisions written down as ADRs."],"location":"Remote"},{"name":"Paperspace","position":"Software Engineer","url":"https://www.paperspace.com/","startDate":"2022-06-01","endDate":"2023-03-01","summary":"MLOps as a service. Acquired by DigitalOcean.","highlights":["Rebuilt Node.js + Stripe billing to support 2.5× YoY revenue growth while keeping payments under 200 ms.","Implemented real-time fraud and sanctions checks that shut down illicit GPU crypto-mining from embargoed regions, reducing chargebacks >50%."],"location":"Remote"},{"name":"Hotel Engine","position":"Senior Software Engineer / Software Engineer","url":"https://www.hotelengine.com/about-us/","startDate":"2021-07-01","endDate":"2022-06-01","summary":"A hotel booking platform and lodging performance network.","highlights":["Introduced bundle splitting, CDN routing, and feature flags, shrinking mean deploy time from 15 min to 6 min for 40+ engineers.","Drove Redux → React Query migration, reducing cold-start data fetches 40% and bundle size 20%."],"location":"Remote"},{"name":"Reynolds & Reynolds","position":"Software Developer","url":"https://www.reyrey.com/company","startDate":"2019-02-01","endDate":"2021-06-01","summary":"Industry leader in automotive technology and digitization.","highlights":["Converted a 20-year-old version-control system for F&I forms from VB6/SQL to COBOL + Pick BASIC - responsible for distributed delivery, usage tracking & billing, and integration with F&I systems. Assumed lead role two weeks after onboarding and delivered on schedule."],"location":"Houston, TX"}],"education":[{"institution":"Rice University","url":"https://www.rice.edu/","area":"","studyType":"B.A.","endDate":"2018-05","score":"3.71"}],"projects":[{"name":"Narrative Nexus","description":"AI-powered companion for tabletop RPG game masters. Co-built with a group of long-time friends who are also software devs.","url":"https://narrative.sh","keywords":["TypeScript","Next.js","Go","Postgres/pgvector","Yjs"]}],"skills":[{"name":"ML / LLM","keywords":["Kubeflow","KServe","vLLM","LangGraph","Langfuse","RAG","Milvus","BAAI/bge-m3","Presidio","AWS Bedrock","Anthropic Claude","MCP"]},{"name":"Infrastructure","keywords":["Kubernetes","Istio (ambient mesh)","ArgoCD","Helm","Kustomize","Terraform","Karpenter","GitHub Actions","cert-manager","external-secrets"]},{"name":"Data","keywords":["PostgreSQL","PostGIS","Aurora","ClickHouse","Snowflake","Drizzle ORM","Kysely","SQLAlchemy","Mongo → PG migrations","Redis / Valkey","BullMQ","Kafka"]},{"name":"Languages","keywords":["TypeScript","Python","Go","SQL"]},{"name":"App Stack","keywords":["NestJS","Fastify","FastAPI","Pydantic","React","Next.js","Jotai","React Query","OPFS","Service Workers"]},{"name":"Observability","keywords":["Grafana","Tempo","Alloy","OpenTelemetry","Mimir","Loki","Pyroscope"]}],"meta":{"canonical":"https://www.kerkstra.dev/api/resume.json","version":"v1.0.0","lastModified":"2026-11-10T14:22:35.737Z"}}