--- title: 'Software Engineer - Europe at Deep Infra Inc.' canonical: 'https://feeny.ai/job/software-engineer-europe-deep-infra-inc-europe-93xwkwkg5qs3' type: 'job' last_seen: '2026-09-14' --- # Software Engineer - Europe at Deep Infra Inc. - **Company:** Deep Infra Inc. - **Location:** Europe - **Employment:** full-time - **Work type:** remote - **Posted:** 2026-03-31 - **Last confirmed live:** 2026-09-14 - **Apply:** https://jobs.gem.com/deep-infra/am9icG9zdDoy5tCXmkY6YWgDwZys_kJk ## Job description ## 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 are looking for strong Software Engineers to join our team. ## Why this role matters You’ll work on designing, building, and scaling infrastructure for serving top open-source AI models in production. This role is ideal for engineers who are already comfortable owning problems end-to-end and want to deepen their experience working on high-impact AI systems. If you’re excited about AI/ML and are looking to work on real systems at scale — we’d love to meet you. ## What You’ll Do - Design, develop, and test inference solutions for state-of-the-art AI models - Implement, optimize, and evaluate AI models using Python, C++, CUDA, and NCCL - Own and operate production model-serving systems, including monitoring and debugging - Build new features, improve system performance, and contribute to overall system design - Participate in code reviews and technical discussions to maintain high engineering standards - Explore and apply new AI/ML techniques to improve model performance and efficiency - Take ideas from concept to production ## What You Bring - Bachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field - 3+ years of relevant experience - Strong fundamentals in data structures, algorithms, and software design - Proficiency in Python and experience working with AI/ML frameworks (e.g., PyTorch, TensorFlow) - Hands-on experience building, shipping, and maintaining software systems - Familiarity with AI models, Transformers, and Diffusers - Experience working with version control (Git) and collaborative development workflows - Ability to debug, optimize, and improve existing systems - Strong communication skills and ability to work independently in a fast-paced environment Bonus - Experience with C++, CUDA, or AI inference - Contributions to open-source ML projects ## Why DeepInfra - Work on cutting-edge AI model serving - the systems that power the next generation of LLMs and multimodal models. - Small team, huge impact: your work ships directly to customers. - Opportunity to learn from engineers building high-performance inference at scale. - Fast-paced environment with ownership, autonomy, and end-to-end responsibility. ## 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. ## About Deep Infra Inc. ## Company Overview - **One-liner**: DeepInfra operates a purpose-built AI inference cloud that provides developer-friendly APIs for running open-source and proprietary machine learning models at scale. - **Entity Type**: Private (Series B) - **Headquarters**: Palo Alto, California, United States - **Founded**: September 2022 - **Founders**: Nikola Borisov (CEO), Georgios Papoutsis, and Yessenzhar Kanapin ## Core Business - **Primary industry/industries**: Artificial Intelligence / Machine Learning Infrastructure - **Target customers**: B2B; startups, enterprises, and developers needing high-throughput, low-latency AI model inference. - **Mission or purpose statement**: To provide a reliable, non-lock-in inference provider built on open-source models, giving companies full control over their AI stack with purpose-built, inference-optimized infrastructure from the GPU hardware layer up to the API. ## Products & Services - **DeepInfra Inference API**: A developer-friendly, OpenAI-compatible API offering access to over 100 open-source and proprietary models (including GLM-5.3-Flash, Kimi K3). Features pay-as-you-go pricing with no long-term contracts. - **Private GPU Clusters**: Dedicated NVIDIA B300 GPU clusters for enterprise customers, available on 5-year terms at significantly below-market rates (e.g., $1.98/GPU-hr vs. $6.50/GPU-hr on public cloud). Scales from 256 to 5,000 GPUs. - **Custom Model Hosting**: A service allowing customers to deploy their own models on DeepInfra’s optimized infrastructure. ## Market Standing - **Valuation/Market Cap**: Not publicly disclosed for the Series B round. - **Key Metric (Funding)**: Total funding of approximately **$153.6M** across 5 rounds, according to LinkedIn. The most recent round was a **$107M Series B** co-led by 500 Global and Georges Harik, with participation from A.Capital Ventures, Crescent Cove, Felicis, NVIDIA, Peak6, Samsung Next, Supermicro, and Upper90. - **Notable Investors/Partners**: NVIDIA, Felicis, 500 Global, Samsung Next, Supermicro, Peak6, A.Capital Ventures, Crescent Cove, Georges Harik. - **Growth Signals**: - Processes over **four trillion tokens per week**. - **25x token volume growth** since Series A. - Workforce grew **312.5% year-over-year** (to 27 employees). - LinkedIn follower count grew **160.7% Year-over-Year**. - Revenue estimated by LinkedIn at **$3.8M annually** (likely early-stage metric). ## Competitive Advantages - **Vertically Integrated Infrastructure**: Unlike many competitors that run on top of public clouds, DeepInfra owns and operates its own GPU hardware in US-based data centers, giving it direct control over cost and performance. - **Cost Leadership**: Advertising pricing up to 70% cheaper than public cloud alternatives for dedicated clusters (e.g., $1.98/GPU-hr for B300). - **Enterprise Security & Compliance**: SOC 2 and ISO 27001 certified with a strict zero data retention policy, ensuring data privacy. - **Open-Source Focus**: DeepInfra is built on the belief that open-source models are the future, offering a wide variety (100+ models) without vendor lock-in. ## Strategic Focus - **Scale and Product Expansion**: The Series B funding is specifically earmarked for scaling the "inference cloud," likely meaning expanding GPU capacity and geographic footprint. - **Supporting Agentic and Complex Workloads**: The platform is optimized for long-horizon agent tasks, coding, and complex multimodal workflows, indicating a focus on the most compute-intensive and emerging AI use cases. - **Enterprise Deployments**: The offering of dedicated, long-term GPU clusters signals a push for larger, more stable enterprise contracts. ## Why Work Here - **Culture & Impact**: DeepInfra operates at the core of the AI infrastructure boom. Employees get to work on hard performance engineering problems (every millisecond matters) that directly affect how AI products are built and scaled across the world. - **Engineering DNA**: The leadership previously built the backend infrastructure for imo messenger, a platform with 1 billion+ downloads. The current team is engineering-heavy (45% of staff in technical roles) and is distributed across the US and Europe (Bulgaria, Poland, Turkey, Serbia). - **Workplace**: The primary office is in Palo Alto, CA, with an **OnSite Workspace** policy (employees work from the physical office). - **Perks & Growth**: As a high-growth startup (312.5% YoY headcount growth), DeepInfra offers significant opportunities for ownership and rapid career advancement. ## Sources 1. [deepinfra.com](https://deepinfra.com/) 2. [deepinfra.com](https://deepinfra.com/about) 3. [linkedin.com](https://linkedin.com/company/deep-infra) 4. [builtin.com](https://builtin.com/company/deep-infra-inc) 5. [cbinsights.com](https://www.cbinsights.com/company/deepinfra) ## Other roles at Deep Infra Inc. - [Forward Deployed Engineer](https://feeny.ai/job/forward-deployed-engineer-deep-infra-inc-palo-alto-sjcnm980d78b) — Palo Alto, CA - [Senior Account Executive](https://feeny.ai/job/senior-account-executive-deep-infra-inc-palo-alto-k9aysft4mave) — Palo Alto, CA - [Software Engineer - Bulgaria, Early Career](https://feeny.ai/job/software-engineer-bulgaria-early-career-deep-infra-inc-sofia-8djq5yr8j0nt) — Sofia, Bulgaria - [Software Engineer](https://feeny.ai/job/software-engineer-deep-infra-inc-palo-alto-gqbz109kbbs9) — Palo Alto, CA - [Director of Marketing](https://feeny.ai/job/director-of-marketing-deep-infra-inc-palo-alto-knzrspg1kber) — Palo Alto, CA - [Software Engineer - Europe, Early Career](https://feeny.ai/job/software-engineer-europe-early-career-deep-infra-inc-europe-90y77nwt3epx) — Europe - [Software Engineer, Early Career](https://feeny.ai/job/software-engineer-early-career-deep-infra-inc-palo-alto-64q7yp6cea3d) — Palo Alto, CA - [Software Engineer Intern (Europe)](https://feeny.ai/job/software-engineer-intern-europe-deep-infra-inc-europe-dkcrbbhn5zdh) — Europe - [Software Engineer Intern (US)](https://feeny.ai/job/software-engineer-intern-us-deep-infra-inc-palo-alto-jrvjh1rz32dv) — Palo Alto, CA - [Developer Relations](https://feeny.ai/job/developer-relations-deep-infra-inc-palo-alto-yxr1ap8fhr8f) — Palo Alto, CA