Remote AI Inference Support Engineer

Together AI; New York (NY); On-site; USD 160,000 - 230,000; Full time

Benefits offered by this job

Health insurance

Startup equity

Remote work

Job summary

Together AI is seeking a Technical Support Engineer to be the first line of defense for customers building training, fine-tuning, and inference solutions. You will work with our GPU clusters and inference services, acting as a product expert and collaborating with product, sales, and engineering to drive improvements.

This remote, full-time role requires 6+ years in customer-facing tech roles, strong Kubernetes experience, and deep AWS/GCP/Azure knowledge.

Qualifications

• 6+ years in a customer-facing technical role or SRE/DevOps
• Experience with Kubernetes in production environments
• Strong AI/ML knowledge and HPC experience
• Proficient with infrastructure as code and Git workflows
• Experience with GPU clusters, inference and fine-tuning
• Excellent cross-functional collaboration and communication

Responsibilities

• Engage with customers to resolve complex technical challenges on GPU clusters and inference/fine-tuning services
• Act as customer-facing SRE to keep inference endpoints healthy on Kubernetes
• Become a product expert and escalate issues to Engineering when needed
• Assist with migrations, validate health, and monitor dashboards for anomalies
• Manage incident communications and provide clear updates
• Contribute infra changes for model deployment and capacity scaling via pull requests
• Flag engine-level bugs with logs and steps
• Collaborate with Engineering, Research, Product, Sales to ensure customer success
• Document configurations, troubleshooting guides, and FAQs
• Provide coverage during holidays, nights, weekends as required

Skills

Customer-facing

Strong communication

Cross-functional collaboration

Problem solving

Ownership

Tools

Kubernetes

Ansible

Terraform

Prometheus

Grafana

SLURM

NFS storage

Vast

Weka

AWS

GCP

Azure

Job description

Together AI is seeking a Technical Support Engineer to be the first line of defense for customers building training, fine-tuning, and inference solutions. You will work with our GPU clusters and inference services, acting as a product expert and collaborating with product, sales, and engineering to drive improvements.

This remote, full-time role requires 6+ years in customer-facing tech roles, strong Kubernetes experience, and deep AWS/GCP/Azure knowledge.