Jobs / Cloudflare
Senior Platform Engineer, Replicate
Cloudflare · London, ENG, United Kingdom
London, ENG, United KingdomExp: 5+ yrsHybrid
Remuneration
Not specified
Location
London, ENG, United Kingdom
Visa sponsorship
No visa sponsorship
Job summary
As a Senior Platform Engineer, you will build and operate distributed systems that receive, schedule, execute, and meter AI inference requests across Kubernetes clusters, multiple cloud providers, and GPU infrastructure. You will lead the migration of models and live traffic to Workers AI while preserving availability, low latency, and API compatibility, and improve scheduling, cold starts, GPU utilization, routing, and production reliability. The platform uses technologies including Go, Python, TypeScript, Kubernetes, AWS, and GCP.
Qualifications
- At least 5 years of experience designing, building, and operating high-throughput, low-latency distributed production systems.
- Strong proficiency in Go, Python, or TypeScript and experience building maintainable, concurrent, well-tested backend services.
- Production experience with Kubernetes, including controllers or operators, scheduling, networking, CNI, or CSI.
- Experience with multi-cloud infrastructure such as AWS, GCP, or bare-metal environments.
- Experience migrating live systems or traffic while maintaining API compatibility under load.
- Experience operating production services, including observability, capacity planning, staged rollouts, and incident response.
- Ability to write architectural proposals and communicate technical tradeoffs clearly.
Responsibilities
- Design and maintain backend services for inference APIs, request queues, workload scheduling, container orchestration, and usage metering and billing.
- Migrate models and live inference traffic to Workers AI using compatibility adapters, dual routing, shadowing, and fallback mechanisms.
- Improve throughput, cold-start latency, and GPU utilization across Kubernetes clusters and edge infrastructure.
- Participate in on-call rotations, mitigate production incidents, write post-incident reviews, and build remediation and observability tools.
- Write technical design documents and conduct code and architecture reviews.
- Mentor engineers and collaborate with infrastructure, networking, storage, security, and product teams.
Skills
AWSCloudflareGCPGoKubernetesPythonTypeScriptOpenTelemetryPrometheus
Work schedule
On-call rotation
Industry
AI inferenceInternet infrastructure
Relocation
No