Customer Success Engineer

About DeepInfra

DeepInfra is building the infrastructure layer for the next generation of AI. We believe open-source models are the future, and companies should have full control over their AI stack without being locked into proprietary providers.

Our inference platform serves trillions of tokens every week across hundreds of production workloads. We build everything from GPU infrastructure to the API layer because every millisecond matters.

We're looking for a Customer Success Engineer to own the technical relationship with the developers and companies running production workloads on our platform.

Why this role matters

When a customer's inference breaks, slows down, or costs more than they expected, you're the person who finds out why and fixes it. You have the technical depth to solve it and the access to do it yourself, instead of routing the ticket to someone else.

You'll work directly with customers ranging from solo developers to enterprises serving millions of requests a day. You'll debug real inference problems, tune their usage, and feed what you learn back into the product. Most investigations run through the terminal: you reproduce the issue, read logs and metrics, find the root cause, and explain it in writing.

This role suits someone who enjoys owning hard technical problems end to end, often with a real customer waiting on a deadline. You're comfortable working on your own and want a say in how our platform supports its customers. We hire for reasoning structured debugging, terminal fluency, and clear writing.

What You'll Do

• Own customer issues end-to-end. This includes to triage, reproduce, root-cause, and resolve technical problems across LLM, embedding, image, TTS, and ASR workloads.
• Debug production inference issues using logs, metrics, and dashboards: latency and TTFT regressions, rate limiting and 429s, error spikes, model behavior changes, and API integration bugs.
• Handle rate limit and capacity requests with real data - analyze a customer's traffic pattern, concurrency, and token throughput, and recommend what actually fixes their problem.
• Resolve billing, usage, and quota questions by tracing per-request ground truth, not guesswork.
• Help customers use the platform well: batching, streaming, prompt caching, structured outputs, tool calling, retries and backoff, and choosing the right model and deployment type for their workload.
• Advise on capacity planning and dedicated deployments - GPU sizing, throughput targets, and cost per million tokens.
• File, prioritize, and drive well-documented bugs and feature requests with Engineering, and follow them through to a customer-facing answer.
• Turn recurring issues into permanent fixes: documentation, internal runbooks, and product changes that stop the ticket from coming back.
• Be the voice of the customer internally - surface patterns to Product and Engineering before they become churn.

What You Bring

• 2+ years in Customer Success Engineering, Support Engineering, Solutions Engineering, Technical Account Management, or a similaole - or software engineering experience and a genuine pull toward customer work.
• A degree or equivalent hands-on background in Computer Science or Engineering.
• Strong technical fundamentals: you're comfortable with HTTP and REST APIs, status codes, headers, streaming responses, authentication, and reading someone else's integration code to spot what's wrong.
• Working proficiency in Python or a similar language - enough to reproduce a customer's issue, write a script, and hand back a working snippet.
• Comfort on the command line and with logs, metrics, and dashboards (Grafana, Prometheus, Loki, or equivalents).
• The ability to take a vague report - "it got slow," "the output looks worse," "I was charged too much" - and turn it into a specific, evidence-backed root cause.
• Excellent written communication: clear, concise, technically precise, and respectful under pressure.
• Strong judgment about when to solve something yourself and when to escalate, and the follow-through to close the loop either way.
• Ability to work independently and prioritize a queue in a fast-moving startup environment.

Bonus

• Exposure to AI/ML infrastructure, such as inference serving, GPUs, or model deployment.
• Experience supporting a developer-facing API or a usage-based billing product.
• Experience being an early or first Customer Success Engineer and building the function's processes and tooling.

Why DeepInfra

• Own the technical customer experience for a platform serving trillions of tokens a week.
• Work on real inference problems at scale, with the access and context to solve them properly.
• Join a small, high-performing team where your work ships fast and customers feel it immediately.
• Help shape how companies build on some of the world's leading open-source AI models.

How we work

Three traits define the people who thrive here, and this role leans on all three.

Initiative. We take ownership and step in where we can add value. Whether it’s starting something new, improving what exists, or helping move ideas forward, we aim to be proactive and thoughtful in how we contribute.

Drive. We’re energized by hard problems. Building AI infrastructure is complex, and we lean into that. We care about doing things well, moving fast, and continuously improving - because solving meaningful challenges is what motivates us.

Grit. Things don’t always work on the first try - and that’s expected. We stay persistent, adapt quickly, and learn as we go. We take setbacks seriously, but not personally, and use them to get better.