Together AI · posted · checked
Technical Support Engineer (Inference)
KubernetesSwiftOn-site · IndiaSenior
Who can apply
On-site · India
Location: Pune or Bangalore, India
About the role
As a Technical Support Engineer at a pioneering AI company, you'll be the first line of defense to support customers as they build out training, fine tuning, and inference solutions with Together AI. You'll dive deep into complex technical challenges, providing swift and effective solutions while serving as a product expert. As a part of the Customer Experience organization, you will collaborate closely with product and sales, driving continuous improvement of our offerings. This is an exciting opportunity for a deeply technical professional passionate about AI and customer success to make a significant impact in a fast-paced, innovative environment.
Required hours
This is a fulltime position working India daytime hours, from Monday-Friday.
Responsibilities
Engage directly with customers to tackle and resolve complex technical challenges involving our cutting-edge GPU clusters and our inference and fine-tuning services; ensure swift and effective solutions every time.
Act as a customer facing SRE to ensure our customer’s Inference endpoints (running on Kubernetes) remain healthy, stable, and performant
Become a product expert in all of our Gen AI solutions, serving as the last line of technical defense before issues are escalated to Engineering and Product teams.
Assist with hardware and platform migrations by validating system health and traffic routing. Monitor dashboards to detect anomalies and escalate with data-backed analysis
Manage customer-facing communications during incidents and degradations; translate deep technical findings (latency regressions, provider issues, network reachability drops) into clear, evidence-backed updates without exposing platform internals
Contribute infrastructure changes for model deployment, capacity rebalancing, and cluster configuration. You will execute infrastructure changes via pull requests (infra-as-code) for tasks such as endpoint configuration, model bringup/bringdown, and capacity scaling
Flag engine-level bugs with logs and reproduction steps for engineering