Engineering Manager - AI Model Infrastructure & Platform

Harvey; San Francisco (CA); On-site; USD 260,000 - 340,000; Full time

Job summary

Harvey is seeking an Engineering Manager for Model Infrastructure in San Francisco to lead a high-performing team responsible for the platform powering every model request. You will partner with AI Research, Product Engineering, Infrastructure, and external providers to ensure reliability, scalability, and cost efficiency as Harvey grows.

You will shape the technical roadmap, build highly reliable provisioning and routing systems, and drive observability and cost reporting across providers.

Qualifications

• 8+ years of software engineering experience with multiple years in management.
• Experience leading teams responsible for large-scale distributed systems or cloud infrastructure.
• Proven ability to guide architectural decisions and mentor senior engineers.
• Experience operating highly available production services with reliability.
• Ability to partner across Engineering, Research, Product, and external vendors.
• Excellent communication and ability to influence technical strategy.
• A passion for building teams and developing engineering talent.

Responsibilities

• Lead and grow a high-performing team of software engineers for Harvey's Model Infrastructure platform.
• Define the technical roadmap for model reliability, scalability, and operational excellence.
• Build reliable systems for model provisioning, capacity management, failover, and incident response across multiple AI providers.
• Own Harvey's multi-provider model platform, including provider integrations, SDK upgrades, API migrations, and onboarding new model providers.
• Evolve the Unified Model Controller and Model Selector to detect degraded models and route traffic by health, latency, quality, compliance, and cost.
• Improve observability through health dashboards, alerts, token usage analytics, cost reporting, and end-to-end model telemetry.
• Partner with Product Engineering to support new model launches, capacity planning, experimentation, and proactive monitoring.
• Lead efforts to improve inference efficiency, reduce infrastructure costs, and increase model utilization across providers.
• Build infrastructure for future model training, data pipelines, and AI platform capabilities.
• Collaborate with leadership on long-term AI infrastructure strategy and vendor relationships.
• Recruit, mentor, and develop engineering talent with a culture of technical excellence and ownership.

Skills

Engineering leadership

Distributed systems

Cloud infrastructure

Observability & reliability

Architectural guidance

Cross-functional leadership

Technical mentorship

Communication skills

Tools

Kubernetes

Cloud platforms

LLM serving

Telemetry/observability tools

Job description

Harvey is seeking an Engineering Manager for Model Infrastructure in San Francisco to lead a high-performing team responsible for the platform powering every model request. You will partner with AI Research, Product Engineering, Infrastructure, and external providers to ensure reliability, scalability, and cost efficiency as Harvey grows.

You will shape the technical roadmap, build highly reliable provisioning and routing systems, and drive observability and cost reporting across providers.