Staff Software Engineer, AI Inference

Our client is dedicated to making the world’s information accessible through audio. As the company grows, the AI team is looking for a Staff Backend Engineer to drive infrastructure scalability, optimize product workflows, and create resilient, end-to-end systems. This role is ideal for individuals passionate about strategic product development in a high-paced environment and eager to take ownership of critical product decisions.

Responsibilities

• Collaborate with machine learning experts, engineers, and product managers to deliver cutting-edge AI features for diverse applications.

• Deploy and operate core machine learning inference workloads for their AI-serving pipeline.

• Innovate on tools, architecture, and techniques to enhance performance, reduce latency, increase throughput, and boost model efficiency.

• Develop tools to identify and address bottlenecks and improve system stability.

Skillset

• Proficient in shipping Python-based services.

• Proven experience overseeing a mission-critical production service.

• Familiar with public cloud environments, preferably GCP.

• Skilled in Infrastructure as Code, Docker, and containerized deployments.

• Preferred: Expertise in deploying high-availability applications on Kubernetes.

• Preferred: Experience in deploying machine learning models to production.

Interested? Apply Now!

48545