AI Platform Engineer ,OpenShift / NVIDIA (Freelance) (Remote)
Ampera Technologies Verified employer
Actively hiring · Posted today · JEV261116D2BA9C03
Job description
AI Platform Engineer, OpenShift / NVIDIA (Freelance)Positions: 1Experience: Ideally 6-10 years.MissionOwn deployment and operation of the underlying enterprise AI/model-serving platform.Mandatory capabilitiesKubernetesRed Hat OpenShiftContainers/Docker/OCIHelmLinuxCI/CDGitOpsNetworkingSecrets/certificatesRegistriesMonitoring/observabilityPriority AI infrastructure experienceOpenShift AIKServeNVIDIA GPU OperatorNVIDIA NIMNVIDIA AI EnterpriseGPU inferenceOpen-weight LLM deploymentvLLM or comparable serving enginesGPU monitoring and performance optimizationCandidates should understand practical inference concepts including tokens/sec, TTFT, prefill vs decode, context length, KV cache, prefix caching, batching, concurrency, GPU memory, quantization and model routing.
Key skills
How to apply
- Sign in or create your free profile — takes about two minutes.
- Apply with one tap — your profile is shared directly with Ampera Technologies.
- Track your application and get updates by email and WhatsApp.