Technical Support Engineer (Inference)

Responsibilities

• Engage directly with customers to resolve complex technical challenges involving GPU clusters, inference, and fine-tuning services
• Act as a customer-facing SRE to ensure Kubernetes-based inference endpoints remain healthy and performant
• Serve as a product expert and the last line of technical defense before escalation to Engineering
• Assist with hardware and platform migrations by validating system health and traffic routing
• Manage customer-facing communications during incidents, translating technical findings into clear updates
• Execute infrastructure changes via pull requests (infrastructure-as-code) for model deployment and capacity scaling
• Flag engine-level bugs with logs and reproduction steps
• Collaborate with Engineering, Research, and Product teams to drive the product roadmap
• Maintain detailed documentation of system configurations, troubleshooting guides, and FAQs

Requirements

• 6+ years in a customer-facing technical role, SRE, DevOps, or infrastructure engineering
• At least 1 year in a support role for an AI service
• Experience with Kubernetes and infrastructure as code (e.g., Ansible)
• Knowledge of AI, ML, GPU technologies, and high-performance computing (HPC)
• Experience with observability tooling like Prometheus and Grafana
• Proficiency in Python, TypeScript, and/or JavaScript
• Familiarity with LLM inference frameworks and LoRA fine-tuning
• Experience with cloud platforms (AWS, GCP, or Azure)
• Ability to work a 4-day weekend shift (Saturday/Sunday plus two weekdays) including on-call coverage

About the Company

Together AI is a research-driven artificial intelligence company on a mission to significantly lower the cost of modern AI systems by co-designing software, hardware, algorithms, and models.