Job alerts, saved jobs and deadline reminders on your phone

Open app

Inference Infrastructure Engineer

Posted Nov 13 (5 days ago)

Key facts

Build GPU scheduling and scalable inference systems at Poolside; remote in EMEA with monthly Paris meetups.

How this salary compares

Estimated €4,080 - €7,100

Est. take-home €2,954 - €4,458

Where and how
Work model
On-siteHybridRemote
Level
Languages required
English

Original job ad

About the role You’ll be working in the compute team focusing on GPU workload scheduling and inference serving optimization. You would partner with the inference team to improve our inference throughput and latency for evals and reinforcement learning. You would collaborate with our scalability team to focus on stabilizing our large scale fault tolerant training. You would also be in close contact with the infra team to make sure our GPU nodes are all healthy and fully utilized. We are one of the key teams to improve the research velocity. Any improvement on our systems has a wide impact on researchers and can contribute to the poolside mission on building a frontier model. Your mission To optimize GPU utilization across the company and to deliver stable and scalable inference serving stack for Poolside’s researchers. Responsibilities Design and develop internal scheduling system to maximize GPU utilization Build API and tooling to help manage the lifecycle of GPU workloads and troubleshoot failures Design and improve inference control plane to speed up model deployment and inference request serving Collaborate with research to improve research velocity continuously Skills & experience Strong programming skills in Go, or other similar languages Strong systems engineering background: distributed systems, schedulers, control planes, or high-throughput data planes. Production experience with Kubernetes internals — controllers, informers, operators — not just deploying to it. Bias toward observability and debuggability: building a system that is easy to navigate when debugging production issues Plus: experience in systems serving large scale inference requests Process Intro call with a member of our team Technical Interview(s) with one of our Members of Engineering Team fit call with the People team Final interview with one of our Founding Engineers Benefits Fully remote work & flexible hours 37 days/year of vacation & holidays Health insurance allowance for you & dependents 16 weeks of flexible, full-pay parental leave Well-being, always-be-learning & home office allowances Company-provided equipment Frequent team get togethers Diverse & inclusive people-first culture

About the role

Summarised by JobCrawls from the job ad above.

Requirements

  • Strong programming skills in Go or a similar language
  • Strong systems engineering background in distributed systems, schedulers, control planes, or high-throughput data planes
  • Production experience with Kubernetes internals, including controllers, informers, and operators
  • Focus on observability and debuggability

Responsibilities

  • Design and develop an internal system to schedule workloads and maximize GPU utilization
  • Build APIs and tools to manage GPU workload lifecycles and troubleshoot failures
  • Improve the inference control plane to accelerate model deployment and inference request serving
  • Collaborate with research to continuously improve research velocity

Skills & technologies

GoDistributed SystemsWorkload SchedulingControl PlanesHigh-throughput Data PlanesKubernetesControllersInformers
Show 3 more
OperatorsObservabilityDebugging

Benefits & perks

Recruitment process

  1. Introductory call with a team member
  2. Technical interview with one or more engineering team members
  3. Team-fit call with the People team
  4. Final interview with a founding engineer

About poolside

poolside logo
poolside · 3 open roles
View company
About the employer

Poolside aims to build artificial general intelligence and create AI systems that support economically valuable work and scientific progress. Its multidisciplinary team combines research, engineering, and business expertise and works toward intelligence systems for software development.

Core values
Hard workIntellectual curiosityObsessionLow egoKind-heartednessCollaborationIntentionalityDiversityInclusionPeople-first culture

Never miss a new Inference Infrastructure Engineer job in Remote - EMEA

Weekly or daily digest. Unsubscribe anytime.

or

We'll email you a link to confirm. Confirming creates a free JobCrawls account for this address so you can manage your alerts. No password. Unsubscribe or delete it any time.