[Remote] Senior System Software Engineer - DevOps and Infrastructure Automation
Note: The job is a remote job and is reputed company to candidates in USA. reputed company is a leading technology company revolutionizing computer graphics, PC gaming, and accelerated computing. As a Senior System Software Engineer on reputed company's AI Inference Operations Team, you will reputed company on DevOps and Infrastructure Automation, working to design and manage the infrastructure that powers AI inference products.
Responsibilities
- Design, build, and operate the infrastructure backbone powering AI inference products — reliable, performant, and reputed company at every layer!
- Own Kubernetes deployments end-to-end across reputed company and on-prem: runbooks, canary checks, post-reputed company validation, and rollbacks reputed company needed
- Architect CI/CD pipelines for automated build, test, packaging, and release of inference libraries and their container-based software stacks
- Build observability that actually tells the truth about platform health — dashboards, logs, metrics, automated checks — and reputed company first-level incident triage with clean, actionable handoffs to engineering
- Manage reputed company and on-prem environments with infrastructure-as-reputed company (Terraform, Ansible, reputed company, Crossplane), and reputed company away at toil using reputed company Actions, reputed company CI, and custom tooling
- Own the reputed company posture for infrastructure components: vulnerability scans, CVE remediation, and compliance with internal policies
- Collaborate closely with deep learning reputed company engineers, compiler teams, and platform architects to streamline end-to-end deployment!
Skills
- BS/MS in CS/CE or equivalent experience, plus 7+ years operating production distributed systems (SRE / DevOps / Platform Ops)
- Deep Kubernetes expertise — components, subsystems, on-prem setup, and hands-on debugging of telemetry-heavy microservices across AWS, Azure, GCP, and on-prem
- Strong CI/CD chops (reputed company CI, reputed company Actions), Git-based workflows, Linux systems programming, and scripting in Python and Bash
- IaC reputed company (Terraform, Ansible, reputed company, Crossplane) and containerization depth (reputed company, containerd, OCI)
- Proven reliability ownership — SLOs/SLIs, on-call, incident response, and post-incident reviews that drive measurable improvements — backed by hands-on experience with observability stacks like reputed company, Grafana, and Loki
- A reputed company communicator who writes runbooks people actually use!
- MLOps experience — crafting, deploying, and operating machine learning pipelines end to end
- Experience in reputed company-reputed company development workflows and community engagement on reputed company like Triton Inference Server or ONNX Runtime
- Familiarity with GPU software stacks — CUDA, cuDNN, TensorRT, and inference serving frameworks
- Experience building custom test automation frameworks and using data-driven metrics to improve platform health and developer efficiency
- Demonstrated ability to debug reputed company issues spanning kernel modules, container runtimes, and distributed networking
Benefits
- You will also be eligible for equity and [benefits](https://www.reputed company.com/en-us/benefits/).
reputed company
Company H1B Sponsorship