Technical Support Engineer

Required Hours

• Full-time position working US daytime hours.
• Weekend coverage is required on Saturday and Sunday, plus two additional weekdays.
• Four-day shift, 10 hours per day, with two additional hours of on-call coverage on Saturdays and Sundays.
• The role initially follows a Monday-to-Friday schedule for ramp-up, then transitions to the four-day weekend shift after full ramping.

Responsibilities

• Engage directly with customers to resolve complex technical challenges involving GPU clusters, inference services, and fine-tuning services.
• Act as a customer-facing SRE to keep customer inference endpoints running on Kubernetes healthy, stable, and performant.
• Become a product expert for generative AI solutions and serve as the final technical escalation point before Engineering and Product.
• Support hardware and platform migrations by validating system health and traffic routing.
• Monitor dashboards, detect anomalies, and escalate issues using data-backed analysis.
• Manage customer communications during incidents and service degradations, translating technical findings into clear, evidence-based updates.
• Execute infrastructure changes through pull requests and infrastructure-as-code workflows for endpoint configuration, model deployment, capacity scaling, and cluster configuration.
• Identify engine-level bugs and provide logs and reproduction steps to Engineering.
• Collaborate with Engineering, Research, Product, Sales, Support, and senior leaders to resolve customer concerns and drive customer success.
• Identify patterns in support cases and translate customer insights into roadmap improvements.
• Maintain documentation covering system configurations, procedures, troubleshooting guides, and FAQs.
• Provide support coverage during holidays, nights, and weekends as required.

Requirements

• 6+ years of experience in a customer-facing technical role, SRE, DevOps, or infrastructure engineering, including at least 1 year supporting an AI service.
• Experience as an SRE or DevOps engineer working with Kubernetes.
• Strong knowledge of AI, machine learning, GPU technologies, and high-performance computing environments.
• Production-level experience with Kubernetes, SLURM, Ansible, high-performance network fabrics, NFS-based storage, and container infrastructure.
• Familiarity with HPC storage systems such as Vast and Weka.
• Ability to diagnose complex network-layer issues and read traces.
• Strong knowledge of Python, TypeScript, and/or JavaScript, with testing and debugging experience using curl and Postman-like tools.
• Expertise with observability tooling such as Prometheus and Grafana at scale.
• Deep familiarity with REST API debugging and HTTP semantics.
• Experience with LLM inference frameworks, LoRA fine-tuning, and common training failure modes.
• Experience with infrastructure as code and Git-based workflows.
• Background in GPU cluster management.
• Experience with AWS, Google Cloud, and/or Azure.
• Foundational knowledge of installing, configuring, administering, troubleshooting, and securing compute clusters.
• Strong technical problem-solving and troubleshooting skills, with a proactive approach to issue resolution.
• Ability to work cross-functionally and manage multiple projects in dynamic environments.
• Excellent communication skills and ability to explain complex technical concepts to nontechnical stakeholders.
• Strong ownership and willingness to learn new skills.

Compensation and Benefits

• US base salary range: $160K–$230K, plus equity and benefits.
• Benefits include health insurance and other benefits.
• Flexible remote-work arrangements.