- Location
- Sofia
- Employment
- Full time
- Level
- Mid level
- Posted
- 24 September
About this role
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. Аnalyze 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, 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 Software Engineering 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 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.
What you get
- Highly competitive compensation package, including additional stock options
- 25 days of paid annual leave, plus up to 3 well-being days per year
- Additional private health insurance, so you’re covered beyond the basics
- Company lunch every working day
- Quarterly performance reviews to support your growth
- Team gatherings, conferences and business trips across Europe and Silicon Valley
As published by Deep Infra. Applications are handled on their site.
Skills this posting mentions
About Deep Infra
DeepInfra is building the infrastructure layer for the next generation of AI, where inference drives real-world impact. Founded in 2022, the company delivers a purpose-built AI inference cloud for high-throughput, production-scale workloads. DeepInfra enables organizations to run open-source and proprietary models, including agentic systems, with speed, efficiency, and control. DeepInfra owns and operates its GPU infrastructure, supports 190+ open-source models, and processes over four trillion tokens per week, offering low-latency performance, OpenAI-compatible APIs, and enterprise-grade security with zero data retention, SOC 2, and ISO 27001 compliance. Careers: https://jobs.gem.com/deep-infra
All 19 openings at Deep InfraOne click, then it is written
Apply to Deep Infra with a resume written for this role.
Queue Customer Success Engineer and I read the posting, rewrite your resume against it, draft the cover letter, and score the fit. Then you press send, or press one button and I fill in Deep Infra’s form for you.
01Drop your resume
A PDF or a LinkedIn URL. About a minute, once.
02I rank the openings
Every weekday morning, the live catalog scored against your history. Up to 20 worth your time, not two hundred links.
03Each one is written up
Resume rewritten for the posting, a cover letter, a fit score. Press send, or let me fill in the form.
- 25 sent a week, free
- No card
- Nothing sent until you say so
More roles at Deep Infra
See all- 19 November
- 16 October
- 8 October
- 8 October
- 24 September
- 24 September
Similar roles elsewhere
See morePut this to work
Paste your career in once. Every application after that is written for you.
Drop a resume or a LinkedIn URL. I rank the live openings against it, rewrite the resume and write a cover letter for the best of them, and fill in the employer's form when you press the button. You read, you decide what goes out.
01Drop your resume
A PDF or a LinkedIn URL. About a minute, once.
02I rank the openings
Every weekday morning, the live catalog scored against your history. Up to 20 worth your time, not two hundred links.
03Each one is written up
Resume rewritten for the posting, a cover letter, a fit score. Press send, or let me fill in the form.
- New matches ranked and written before you are up.
- Every bullet stays inside what your history supports. Nothing invented.
- Queued, submitted, interviewing, offer: one screen, not a spreadsheet.
Free, no card. Up to 25 applications sent a week, and nothing is sent until you say so.
Listed from the job board Deep Infra publishes. Refolk is not the employer and does not handle their hiring. Applications go to Deep Infra directly.
Hiring at Deep Infra? Post this role to the Refolk talent pool for $299, once. No commission, refunded if I find nobody. Post a role for $299