The point where experts and best companies meet
Share
What you will be doing:
Support and work on groundbreaking Generative AI inferencing workloads running in a globally-distributed heterogeneous environment spanning 60+ edge locations plus all major cloud service providers. Ensure the best possible performance and availability on current and next-generation GPU architectures.
Collaborate closely with the service owner, architecture, research, and tools teams at NVIDIA to achieve ideal results for AI problems at hand.
Monitoring & supporting critical high-performance, large-scale services running multi-cloud.
Participate in the triage & resolution of sophisticated infra-related issues.
Maintain services once live by measuring and monitoring availability, latency, and overall system health using metrics, logs, and traces.
Scale systems sustainably through mechanisms like automation and evolve systems by pushing for changes that improve reliability and velocity.
Practice balanced incident response and blameless postmortems.
Be part of an on-call rotation to support production systems and lead significant production improvement around tooling, automation, and process.
Architect, design, and code using your expertise to optimize, deploy and productize services.
What we need to see:
8+ years of experience operating & owning end-to-end availability and performance of mission-critical services in a live-site production environment, either as an SRE or Service Owner.
BS degree in Computer Science or a related technical field involving coding (e.g., physics or mathematics), or equivalent experience
Solid understanding of containerization and microservices architecture, K8s. Excellent understanding of the Kubernetes ecosystem and best practices with K8s.
Ability to dissect complex problems into simple sub-problems and use available solutions to resolve them.
Technical leadership beyond development that includes scoping, requirements capturing, leading and influencing multiple teams of engineers on broad development initiatives.
Lead significant production activities, including change management, post-mortem reviews, workflow processes, software design, and delivering software automation in various languages (Python, or Go ) and technologies (CI/CD auto-remediation, alert correlation).
Best in understanding SLO/SLIs, error budgeting, KPIs, and configuring for highly sophisticated services.
Experience with the ELK and Prometheus stacks as a power user and administrator.
Excellent understanding of cloud environments and technologies, especially AWS, Azure, GCP, or OCI.
Proven strengths in identifying, mitigating, and root-causing issues while continuously seeking ways to drive optimization, efficiency, and the bottom line.
Ways to stand out from the crowd:
Exposure to containerization and cloud-based deployments for AI models.
Excellent coding: Python, Go (Any similar language).
Prior experience driving production issues and helping with on-call support and understanding of Deep Learning / Machine Learning / AI.
Experience with Cuda, PyTorch, TensorRT, TensorFlow, and/or Triton as well as experience with StackStorm and similar automation platforms is a bonus.
Understanding of observability instrumentation techniques and best practices, including OpenTelemetry.
These jobs might be a good fit