Technical Support Engineer (Inference)

About the role

In this role, you will be the first line of defense supporting customers as they build out training, fine tuning, and inference solutions with Together AI. You will dive deep into complex technical challenges, providing swift and effective solutions while establishing yourself as a product expert. You will collaborate closely with product and sales teams, driving continuous improvement of our offerings from a customer experience perspective. This position is designed for a deeply technical professional passionate about AI and customer success who wants to make a significant impact in a fast-paced, innovative environment. You will operate with a high degree of ownership and flexibility to ensure consistent and reliable service for our customers across demanding time zones.

Key facts

What you'll do

Engage directly with customers to tackle and resolve complex technical challenges involving our 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.

Collaborate seamlessly across Engineering, Research, and Product teams to address customer concerns; collaborate with senior leaders both internally and externally to ensure the highest levels of customer satisfaction.

Transform customer insights into action by identifying patterns in support cases and working with Engineering and Go-To-Market teams to drive Together's roadmap (e.g., future models to support).

Maintain detailed documentation of system configurations, procedures, troubleshooting guides, and FAQs to facilitate knowledge sharing with team and customers.

Be flexible in providing support coverage during holidays, nights and weekends as required by business needs to ensure consistent and reliable service for our customers.

Requirements

6+ years of experience in a customer-facing technical role, SRE, DevOps, or infrastructure engineering, with at least 1 year in a support role for an AI service.

Experience as an SRE or DevOps engineer working with Kubernetes.

Strong technical background, with knowledge of AI, ML, GPU technologies and their integration into high-performance computing (HPC) environments.

Advanced, production-level experience with infrastructure services (e.g., Kubernetes, SLURM), infrastructure as code solutions (e.g., Ansible) high-performance network fabrics, NFS-based storage management, and container infrastructure.

Familiarity with operating storage systems in HPC environments 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 using curl and Postman-like tools.

Demonstrated expertise with observability tooling (e.g., Prometheus, Grafana) at scale.

Deep familiarity with REST API debugging and HTTP semantics.

Experience with LLM inference frameworks and LoRA fine-tuning and common training failure modes.

Experience with Infrastructure as Code and Git-based workflows.

Background in GPU cluster management.

Cloud platform experience (AWS, GCP, and/or Azure).

Foundational understanding in the installation, configuration, administration, troubleshooting, and securing of compute clusters.

Complex technical problem solving and troubleshooting, with a proactive approach to issue resolution.

Ability to work cross-functionally with teams such as Sales, Engineering, Support, Product and Research to drive customer success.

Strong sense of ownership and willingness to learn new skills to ensure both team and customer success.

Excellent communication and interpersonal skills, with the ability to explain complex technical concepts to non-technical stakeholders.

Ability to operate in dynamic environments, adept at managing multiple projects, and comfortable with frequent context switching and prioritization.

Practical notes

This is a fulltime position working US daytime hours. The role will work both weekend days (Saturday and Sunday) as well as two additional weekdays. This is a 4-day shift, 10 hours per day, with 2 additional hours of on-call coverage on Saturdays and Sundays. The role would start as a Monday to Friday role for the first few months to allow for ramping up and learning from teammates. After being considered fully ramped, the role would transition to the 4-day weekend shift.