Lead a critical platform software engineering team responsible for the layer between clients and backend services. This role involves managing proxy and L7 services, API Gateway, and inference gateways for AI traffic. You will shape the technical direction, build and develop the team, and ensure end-to-end ownership of these vital services from design through production.

This team tackles complex challenges including request routing, TLS termination, connection management, and maintaining predictable tail latency under heavy load. They also focus on API gateway functionalities like authentication, authorization, rate limiting, and providing a secure, self-service platform for API exposure. Furthermore, the team addresses the unique demands of AI inference traffic, optimizing routing, queuing, and capacity efficiency for long-running, streamed requests on expensive GPU resources.

This is an opportunity to make a significant impact on system performance, availability, and correctness, directly influencing all downstream operations.

As a Senior Manager, you will be instrumental in building and nurturing a high-performing engineering team. This includes hiring exceptional talent, setting clear expectations, providing constructive feedback, and fostering professional growth.

You will collaborate with leadership and partner teams to define the team's strategic roadmap and prioritize initiatives. Your technical insight will be crucial for reviewing designs, evaluating trade-offs, and making informed decisions.

Owning the operational health of the services is paramount. This involves active participation in on-call rotations, leading incident response, conducting thorough postmortems, and driving reliability improvements. You will also work cross-functionally with networking, security, platform, and ML infrastructure teams to resolve complex, boundary-spanning issues.

We are seeking an experienced leader with a proven track record of managing engineers who build and operate robust distributed systems in production environments. A strong technical foundation is essential, with expertise in at least one of the following areas: proxies and load balancing, API gateways, service mesh, networking, or high-throughput backend services.

Candidates should possess experience managing latency-sensitive services, including hands-on involvement in on-call duties and incident management. Experience in initiating and building new ventures, such as establishing a team, launching a novel service, or guiding a product from its initial design to successful production deployment, is highly valued.

A history of successful hiring and a commitment to developing engineers are key qualifications. While not strictly required, familiarity with Envoy, NGINX, LLM inference serving concepts, and building internal platforms would be advantageous.