Senior Software Engineer (Serverless)

About This Opportunity

We are representing a confidential AI cloud infrastructure organization seeking a Senior Software Engineer to build their GPU-native serverless platform. This is a high-ownership role where you'll architect and ship core components that power production AI workloads at scale. You'll own the hardest technical problems—cold-start latency, GPU scheduling, multi-tenant isolation—and set the engineering standard for the team through design leadership and operational excellence.

This position is based in London with a hybrid work arrangement.

Responsibilities

• Design and build core platform components including the control plane, scheduler, runtime, autoscaler, and customer-facing APIs
• Solve complex distributed systems challenges: cold-start latency optimization, GPU scheduling under contention, multi-tenant isolation, fair-share quotas, and edge request routing
• Drive technical direction for your domains—own architecture decisions, author design documents, and align teams behind chosen approaches
• Elevate engineering standards through code reviews, design reviews, and technical mentorship
• Operate the service with SRE discipline: define SLOs, build observability tooling, lead incident response, and ensure postmortems drive platform improvements
• Collaborate directly with customers on architecture reviews, performance escalations, and production issues requiring deep technical engagement
• Partner with product, go-to-market, and infrastructure teams to translate customer requirements into coherent technical roadmaps

What We're Looking For

Required qualifications:

• 7+ years of professional software engineering experience shipping production distributed systems at scale
• Strong proficiency in Golang, or demonstrable ability to quickly adopt it
• Deep Kubernetes and container orchestration expertise—you've operated these systems in production, not just deployed them
• Strong distributed systems fundamentals: consistency vs. availability trade-offs, queueing theory, backpressure, retry strategies, idempotency, and multi-tenancy patterns
• Proven experience designing and operating high-throughput, low-latency services with understanding of performance optimization
• Track record as a technical leader who drives design discussions, unblocks teammates, and tackles complex problems others avoid
• Ability to write reliable, maintainable code and debug complex production issues
• Collaborative team-oriented approach

Bonus qualifications:

• Experience building serverless or function-as-a-service platforms (Knative, AWS Lambda, GCP Cloud Run, Cloudflare Workers, or similar frameworks)
• GPU scheduling expertise including Kubernetes device plugins, MIG, MPS, time-slicing, or NVIDIA GPU Operator
• ML inference platform experience with vLLM, TensorRT-LLM, Triton Inference Server, SGLang, or model loading strategies
• Cold-start optimization knowledge at the runtime, image, or snapshot level (FireCracker, gVisor, checkpoint/restore, image streaming)
• Experience writing Kubernetes operators using Go with controller-runtime or kubebuilder
• Open-source contributions to serverless, scheduling, or inference ecosystems

The interview process includes coding assessments.

How We Work With You

When you apply through Get A Job.ai, our recruiting team will review your background and conduct an initial screening to understand your experience and career goals. If there's a strong match, we'll submit your profile to our client for consideration. Throughout the process, we'll be your advocate and primary point of contact.

Please apply exclusively through Get A Job.ai—do not contact the client directly. All communication regarding this opportunity should go through our talent team to ensure a coordinated and professional process.

Pay

Compensation details will be discussed during the screening process and are competitive for senior engineering roles in the London market.

Equal Opportunity: Get A Job.ai is committed to inclusive recruiting practices. We welcome applicants from all backgrounds and will work with clients to ensure fair consideration. Candidates must be authorized to work in the United Kingdom.