Technical Support Engineer Inference

Skills

About the Role

You will support customers using GPU clusters, inference, and fine-tuning services. You will maintain endpoint health, investigate incidents, validate migrations, communicate customer impacts, contribute infrastructure changes through pull requests, diagnose bugs, and document troubleshooting procedures. You will work a four-day India daytime weekend shift after ramping up.

Requirements

• 6+ years of customer-facing technical, SRE, DevOps, or infrastructure engineering experience
• At least 1 year of AI-service support experience
• Knowledge of AI, machine learning, GPU technologies, and HPC environments
• Production experience with Kubernetes, SLURM, Ansible, networking, NFS storage, and containers
• Experience operating Vast or Weka storage systems
• Ability to diagnose network-layer issues and read traces
• Knowledge of Python, TypeScript, or JavaScript
• Experience with curl, API testing, observability, Prometheus, and Grafana
• Knowledge of REST APIs and HTTP semantics
• Experience with LLM inference frameworks and LoRA fine-tuning
• Experience with infrastructure as code and Git workflows
• GPU cluster management experience
• AWS, GCP, or Azure experience

Responsibilities

• Resolve customer technical challenges involving GPU clusters, inference, and fine-tuning services
• Maintain the health, stability, and performance of customer inference endpoints
• Validate system health and traffic routing during hardware and platform migrations
• Monitor dashboards and escalate anomalies with data-backed analysis
• Communicate customer impacts during incidents and degradations
• Contribute infrastructure changes through pull requests
• Flag engine-level bugs with logs and reproduction steps
• Identify support patterns and inform roadmap decisions
• Maintain system and troubleshooting documentation
• Provide support coverage during holidays, nights, and weekends as needed

Benefits

• Startup equity
• Health insurance
• Remote-work flexibility