Engineering Manager, Model Infrastructure
1 hour agoLeadSalary: 260K - 350KSan Francisco, USAOnsiteFull TimeEngineering ManagementJobs by Harvey
HarveyVisit Harvey website
Harvey is an AI platform for legal and professional-services organizations.
Series F+Recently funded
Distributed
About Harvey
Harvey provides agents and collaborative tools for legal work, including legal research, document analysis, secure workspaces, contract intelligence, and organization-level analytics.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You will lead the team behind the platform powering every model request. You'll define the roadmap for reliability and scalability, build systems for provisioning, failover and incident response across multiple AI providers, evolve the Unified Model Controller and Model Selector, improve observability and cost efficiency, and lay the infrastructure foundation for training Harvey's own models.
Requirements
- 8+ years of software engineering experience, including multiple years managing engineering teams
- Experience leading teams responsible for large-scale distributed systems or cloud infrastructure
- Strong technical background to guide architectural decisions and mentor senior engineers
- Experience operating highly available production services
- Experience building scalable, observable, automated, cost-optimized platforms
- Strong cross-functional leadership skills
- Excellent communication skills
Responsibilities
- Lead and grow a team of software engineers for the 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
- Own the multi-provider model platform including integrations, SDK upgrades, API migrations, and onboarding
- Evolve the Unified Model Controller and Model Selector to route traffic by health, latency, quality, compliance, and cost
- Improve observability through dashboards, alerting, token usage analytics, cost reporting, and telemetry
- Partner with Product Engineering on model launches, capacity planning, experimentation, and monitoring
- Lead initiatives to improve inference efficiency and reduce infrastructure costs
- Build infrastructure for future model training including data pipelines and training environments
- Partner with executive leadership on AI infrastructure strategy and vendor relationships
- Recruit, mentor, and develop engineering talent
Benefits
- Equity
