Staff Software Engineer - Serverless

Runware

2d • Remote

About The Position

Runware is looking for a Staff/Senior Software Engineer to technically lead and build its serverless platform. The position is part of a small team working closely with senior leadership to bring a new product line to market. Runware is expanding from model APIs to a platform where developers can deploy models and run AI workloads without managing GPUs, servers, or infrastructure. The engineer will build the software layer connecting Runware’s proprietary high-performance sonic inference engine with an accessible developer experience.

This role combines technical leadership with solving platform challenges and building clean, simple systems. The work will help enterprises, model labs, and developers move from idea to production and scale without having to build and operate infrastructure themselves.

Runware is a remote-first collective that meets in person twice a year. Core hours are set aside for collaboration and calls, with flexibility outside those hours. The company emphasizes sustainable performance and makes space for employees to recharge after major releases and milestones.

Requirements

• Strong experience as a Staff Engineer, Senior Software Engineer, Backend Engineer, Platform Engineer, or in a similar role.
• Experience building backend services, distributed systems, developer platforms, or workload orchestration systems.
• Strong understanding of asynchronous processing, queues, scheduling, retries, back pressure, and failure handling.
• Comfort working across APIs, control planes, workers, databases, and observability systems.
• Strong engineering fundamentals in one or more backend languages; Go is preferred.
• Good judgment in balancing reliability, latency, scale, cost, and developer experience.
• Clear communication, strong ownership, and ability to lead technical direction in a fast-moving environment.

Nice To Haves

• Experience building serverless platforms, job execution systems, container platforms, or compute orchestration systems.
• Experience with GPU-backed workloads, AI/ML inference, model serving, batch processing, or high-performance computing.
• Familiarity with technologies such as vLLM, TensorRT, Triton, Kubernetes, Nomad, or Knative.
• Experience improving workload performance through batching, autoscaling, model warm-up, caching, request routing, or queue management.
• Experience with multi-tenant isolation, sandboxing, quotas, rate limits, resource accounting, or usage-based billing.

Responsibilities

• Build the core systems behind Runware’s serverless platform, including workload execution, routing, scheduling, isolation, and scaling using its inference engine.
• Enable developers to deploy models and run AI workloads through a simple SDK without managing GPUs, servers, queues, or infrastructure.
• Design and improve the serverless execution control plane, including APIs, workers, lifecycle management, retries, and failure handling.
• Work with infrastructure and ML teams to improve workload startup time, GPU utilization, model warm-up, caching, and placement.
• Build observability systems that make serverless workloads easy to monitor, debug, and operate globally at scale.
• Lead technical design, mentor other engineers, and help define engineering standards for a new product area.

Benefits

• Generous paid time off, including vacation, sick days, and public holidays.
• Meaningful stock options.
• Remote-first work-from-home setup in locations where the company can employ the worker.
• Flexible hours outside core collaboration blocks.
• Paid maternity, paternity, and caregiver leave.
• Twice-yearly company retreats.
• Time to unplug and recharge after major releases and milestones.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed