Technical Support Engineer (Inference) - India Weekends
Together AI · Pune or Bangalore, India · Remote
CHECKED 3H AGO
Infrastructureremotesenior
At a glance
Highlights
- Support customers building training, fine-tuning, and inference solutions.
- Ensure customer inference endpoints stay healthy, stable, and performant.
- Drive product roadmap by turning support insights into action.
What they offer
- Startup equity
- Health insurance
- Remote work flexibility
Ideal candidate
Deeply technical, customer-obsessed engineer with SRE instincts who thrives on complex problem-solving, clear communication during incidents, and shaping AI products in a fast-paced environment.
Requirements
- 6+ years in customer-facing technical, SRE, DevOps or infrastructure role, including 1+ year supporting an AI service
- Strong background in AI, ML, GPU technologies and HPC environments
- Advanced production experience with Kubernetes, SLURM, Ansible, high-performance networking, NFS storage and containers
- Familiarity operating HPC storage systems such as Vast and Weka
- Proven ability to diagnose complex network-layer issues and read traces
- Strong knowledge of Python, TypeScript and/or JavaScript with testing/debugging
- Experience with cloud platforms including AWS, GCP and/or Azure
- Foundational understanding of installing, configuring, administering, troubleshooting and securing compute clusters
- Excellent communication skills explaining complex concepts to non-technical stakeholders
- remote policy
- Flexibility in terms of remote work for the respective hiring region
Lab profile
About Together AI
AI-native cloud for training and inference on large-scale GPU infrastructure for AI apps and agents.
What they build
- AI-native cloud platform
- GPU clusters for training and inference
- Platform for AI applications and agents
Known for
- Operating large-scale GPU fleets
- Automated infrastructure at massive scale
- Multi-site data center deployment
Key facts
- Over 1M developers
- Operates one of the world's largest GPU fleets
- Infrastructure managing tens of thousands of GPUs