Join Cloudflare as a Senior Platform Engineer to design and operate distributed systems for AI inference on a global network.
Posted by employer 18 hours ago
First seen on Joblaze 29 minutes ago
Last verified on the company career page 29 minutes ago
Joblaze summary
In the role of Senior Platform Engineer at Cloudflare, the individual will focus on designing and operating distributed systems that manage customer inference requests across various cloud environments. Key skills include proficiency in Go, Python, or TypeScript, along with extensive experience in Kubernetes and multi-cloud infrastructure. This position is ideal for seasoned engineers with a strong background in high-throughput systems and a knack for operational excellence. The team emphasizes collaboration and continuous improvement, making it a fitting environment for those who thrive in complex production settings.
Quick facts
- Is the Senior Platform Engineer, Replicate role remote?
- It's hybrid — Cloudflare expects some on-site time in Austin, TX, United States.
- How much experience is required?
- At least 5 years of relevant experience for this Senior Platform Engineer, Replicate role.
- Where is the role based?
- Cloudflare is hiring for this position in Austin, TX, United States.
- What's the tech stack?
- Joblaze extracted these technologies from the posting: AWS, GCP, Go, Kubernetes, Python, TypeScript.
- What seniority level is this role?
- Cloudflare targets senior candidates for this position.
- Is this full-time or contract?
- Full-time for this Senior Platform Engineer, Replicate role at Cloudflare.
From the original posting
About Us
Available Locations: Austin, TX | London, UK (Hybrid)
Role Summary
Replicate is now part of Cloudflare, and we are bringing its AI inference platform onto Cloudflare's global network and Workers AI. As a Senior Platform Engineer on the Replicate team, you will design, build, and operate the core distributed systems that accept, schedule, execute, and meter customer inference requests across Kubernetes clusters, multiple cloud providers, and heterogeneous GPU infrastructure. You will be a key technical driver in migrating Replicate’s models, workloads, and traffic onto Workers AI while maintaining high availability, low latency, and seamless backwards compatibility for existing customers. You will partner closely with engineers across Workers AI, core infrastructure, and product teams to solve hard problems in container orchestration, cold-start optimization, multi-tenant GPU scheduling, and high-throughput API routing. We are looking for an engineer who thrives in complex production environments, brings pragmatic architectural judgment, and elevates the engineering bar through strong code, thoughtful design reviews, and technical mentorship.
Role Responsibilities
- Architect and Build Core Platform Systems: Design, implement, and maintain the backend services powering Replicate's inference lifecycle—including public APIs, request queueing, workload scheduling, container runtime orchestration, and usage metering/billing.
- Drive the Workers AI Migration: Architect and execute the technical migration of Replicate models and live inference traffic to Workers AI, building translation layers, dual-routing/shadowing pipelines, API compatibility adapters, and graceful fallback mechanisms with zero customer disruption.
- Optimize Performance, Scale, and Cost: Profile and improve system throughput, cold-start latency, and GPU utilization across multi-cloud Kubernetes clusters and Cloudflare's edge infrastructure.
- Ensure Production Reliability: Participate in the team’s on-call rotation, lead triage and mitigation during live production incidents, author thorough post-incident reviews, and build automated remediation and observability tooling.
- Raise the Technical Bar: Author clear technical design documents (RFCs), conduct thorough code and architecture reviews, and mentor fellow engineers on distributed systems best practices and operational excellence.
- Cross-Team Technical Collaboration: Partner directly with Workers AI, networking, storage, and security engineering teams across Cloudflare to integrate Replicate’s platform primitives into Cloudflare’s broader AI stack.
Role Requirements (Must-Have Skills)
- Distributed Systems Experience: 5+ years of software engineering experience designing, building, and operating high-throughput, low-latency distributed production systems with strict availability requirements.
- Strong Programming Proficiency: Deep hands-on proficiency in Go, Python, or TypeScript, with experience writing clean, concurrent, maintainable, and well-tested backend services.
- Cloud & Container Orchestration: Extensive production experience with Kubernetes (custom controllers/operators, scheduling, networking, CNI/CSI) and multi-cloud infrastructure (AWS, GCP, or bare-metal environments).
- Migration & Zero-Downtime Delivery: Proven track record of re-architecting live systems, executing large-scale data or traffic migrations, and maintaining strict API backwards compatibility under load.
- Operational Excellence: Hands-on experience operating tier-1 production services, including observability (metrics, distributed tracing, structured logging), capacity planning, staged rollouts, and incident response.
- Clear Technical Communication: Ability to write concise architectural proposals and communicate complex technical tradeoffs clearly across distributed engineering teams.
Please submit a resume or CV with your application.
Nice-to-Have Skills
- Experience building or operating GPU infrastructure, ML inference engines (e.g., Triton, vLLM, Cog), or container image distribution/caching systems optimized for fast cold starts.
- Experience with Cloudflare Workers, Workers AI, or edge/serverless compute platforms.
- Familiarity with high-performance networking, load balancing, and multi-region traffic routing.
- Experience working on developer-facing APIs, usage-based billing/metering pipelines, or multi-tenant sandboxing and workload isolation.
What Makes Cloudflare Special?
Standard company text repeated across Cloudflare's postings is omitted here.