What You'll Do
Own Operational Systems Architecture: Design and evolve distributed systems on GCP (Cloud Run, Pub/Sub, BigQuery) that support scheduling, task assignment, and operational workflows. Make final decisions on service boundaries, schemas, and technology trade-offs across Go, Python, and TypeScript.
- AI-Powered Operations: Lead integration of AI into operational workflows using open-source LLMs, embeddings, and speech models. Define prompt strategies, evaluations, and safeguards (e.g., LangFuse) to ensure AI systems are reliable and usable by operations teams.
- Human-in-the-Loop Workflows: Build and improve systems that coordinate AI decisions with human execution—assigning work, routing tasks, and handling exceptions at scale.
- Operational Excellence: Champion observability, reliability, and data quality. Oversee event-driven ingestion and automated QA for call transcripts and healthcare data (FHIR / Medplum).
- Player-Coach Execution: Contribute code to critical paths while leading technical initiatives. Identify gaps, unblock teams, and ensure projects ship end-to-end.
- Cross-Functional Alignment: Partner deeply with Operations, Product, Design, and Clinical Ops to translate operational constraints into clear technical solutions and trade-offs.
Who You Are
- 8+ years of software engineering experience, with 2+ years leading projects or acting as a Tech Lead.
- Staff-level scope or equivalent technical impact.
- Strong experience building operational products involving scheduling, task assignment, routing, or workforce coordination (e.g., DoorDash, Uber, logistics, marketplaces).
- Hands-on experience working with AI systems in production environments.
- Expert-level proficiency in Go, Python, or TypeScript/Node, with the ability to review code across the stack.
- Deep experience with distributed systems, containerized deployments (Docker, Kubernetes, Cloud Run), and event-driven architectures.
Preferred:
- AI / LLM Fluency: Experience hosting or integrating open-source models (vLLM, Ollama) and understanding modern RAG architectures.
- Healthcare & Compliance: Prior experience in regulated environments (HIPAA, SOC 2) or healthcare data standards (FHIR, HL7).
- Strong Communicator: Able to write clear RFCs and explain technical decisions to non-technical operations stakeholders.