2 hours ago
Base Salary
$231k - $340k/yr
Responsibilities
- Lead the design and implementation of Harvey’s Model Infrastructure platform.
- Build highly available, low-latency, and operationally excellent systems for AI inference.
- Design and improve the Unified Model Controller and Model Selector for reliability-, latency-, quality-, compliance-, and cost-based traffic routing.
- Develop model provisioning, capacity management, failover, and traffic-engineering systems across multiple AI providers.
- Integrate model providers and maintain provider APIs and SDKs.
- Build observability capabilities including health dashboards, alerting, token usage analytics, cost reporting, and end-to-end telemetry.
- Support model launches, experimentation, and proactive monitoring of production AI workloads.
- Drive capacity planning, utilization optimization, and cost visibility.
- Build infrastructure foundations for model evaluation, training, and deployment.
- Lead cross-functional technical initiatives and mentor engineers.
Requirements
- 7+ years of software engineering experience building large-scale distributed systems.
- Experience designing and operating highly available production services.
- Strong programming skills in Go, Java, Python, Rust, or C++.
- Deep understanding of distributed systems, cloud infrastructure, networking, and observability.
- Experience leading technical projects across multiple engineering teams.
- Ability to balance long-term architecture with pragmatic execution.
- Strong communication and collaboration skills.
- Experience with AI infrastructure, LLM serving, or machine learning platforms is preferred.
- Experience with model routing, inference gateways, or policy-based serving systems is preferred.
- Experience with OpenAI, Anthropic, Azure OpenAI, Fireworks, Baseten, or open-source LLMs is preferred.
- Experience with Kubernetes, cloud infrastructure, and service mesh technologies is preferred.
- Experience with large-scale observability and SRE best practices is preferred.
- Experience with Kafka, Spark, Flink, Airflow, or Iceberg is preferred.
- Familiarity with GPU infrastructure or model training platforms is preferred.
Tech Stack
Categories
About Harvey
Harvey is domain-specific AI for legal and professional services. Adopted by Fortune 500 companies like AT&T, Verizon, Cox, Koch, KKR, Bridgewater, more than 100,000 lawyers across 2,400+ customers in 70 countries and over 75% of AmLaw 100 law firms rely on Harvey to advance legal expertise faster across contract analysis, due diligence, compliance, and litigation. Backed by Sequoia Capital, OpenAI, GV, Kleiner Perkins, Coatue and EQT, Harvey is the trusted partner in modernizing the legal industry.