> Markdown version of [/jobs/ext/3843696-staff-software-engineer-core-infrastructure](https://www.wearedevelopers.com/jobs/ext/3843696-staff-software-engineer-core-infrastructure). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Staff Software Engineer, Core Infrastructure

- **Company:** Harvey, Inc.
- **Location:** New York, NY, United States
- **Contract:** Permanent contract
- **Skills:** Application Programming Interfaces (APIs), Artificial Intelligence, Amazon Web Services, Microsoft Azure, Cloud Computing, Cloud Computing Security, Code Review, Computer Programming, Distributed Systems, Fault Tolerance, Python (Programming Language), Redis, Datadog, Pulumi, Load Balancing, Grafana, Multi-Cloud, Rate Limiting, AI Platforms, Kubernetes, Infrastructure Automation Frameworks, Deployment Automation, Sentry, Machine Learning Operations, Terraform, Pagerduty
- **Published:** October 20, 2026
- **Apply:** https://www.juju.com/job/23_73AB23CC56A089C470791E3560F751DA

## About the Role

technical leadershipRepresentative ProjectsDesign and implement a next-generation model proxy architecture that routes millions of daily inference requests while maintaining model API compatibility and enabling seamless model integrationBuild distributed rate limiting and quota management systems using Redis-backed algorithms to handle bursty traffic patterns without degrading user experienceArchitect multi-region deployment strategies that meet strict data residency requirements for global enterprise customersDevelop comprehensive observability infrastructure with granular SLA monitoring, burn rate alerts, and detailed token attribution for cost trackingLead the evolution of our CI/CD pipelines to improve developer velocity while maintaining production stabilityWhat You Have10+ years of experience in Infrastructure Engineering or Platform Engineering in a production environmentLong track record building and scaling complex, large-scale distributed systemsDeep proficiency with
cloud infrastructure platforms (Azure preferred; GCP or AWS experience transfers well)Strong fluency in Infrastructure as Code (IaC) tools - Terraform, Pulumi, or CloudFormationSolid understanding of Kubernetes, container orchestration, networking, and cloud security at scaleExperience with observability tools (Datadog, Sentry) and incident response practices (PagerDuty, Incident.io)Strong programming skills in Python, Go, or similar languagesExcellent problem-solving skills, a "spidey sense" of where things could go wrong, and a commitment to operational excellenceNice to HaveExperience building infrastructure for AI/ML workloads or high-throughput inference systemsBackground with distributed rate limiting, load balancing, or quota management systemsExperience operating multi-tenant platforms with strict security and compliance requirementsTrack record of leading complex cross-functional projects and delivering measurable impactCompensation Range$201,000 - $264,000
USD

## Description

We use an in-person work model and offer relocation assistance to new employees.What You'll DoDesign and build scalable, fault-tolerant infrastructure systems that power Harvey's AI platform across multiple cloud regionsOwn and evolve our multi-cloud infrastructure (Azure, GCP), including Kubernetes orchestration, networking, and container managementLead technical initiatives around observability, incident response, and operational excellence - building systems that enable rapid detection and resolution of issuesArchitect and optimize our distributed systems for reliability, including load balancing, quota management, and failover mechanismsPartner with Product Engineering and Security teams to ensure our infrastructure is an accelerant, not a constraintDrive infrastructure-as-code practices using tools like Terraform and Pulumi to enable reproducible, auditable deploymentsMentor engineers and raise the technical bar across the organization through code reviews, design reviews, and