Software Engineer

DeepInfra is looking for early-career Software Engineers to join our team. 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, have built and shipped projects, and are looking to work on real systems at scale — we’d love to meet you.What You’ll DoDesign, develop, and test inference solutions for state-of-the-art AI modelsImplement, optimize, and evaluate AI models using Python, C++, CUDA, and NCCLOwn and operate production model-serving systems, including monitoring and debuggingBuild new features, improve system performance, and contribute to overall system designParticipate in code reviews and technical discussions to maintain high engineering standardsExplore and apply new AI/ML techniques to improve model performance and efficiencyTake ideas from concept to productionWhat You BringBachelor’s or Master’s degree in Computer Science, Computer Engineering, or a related field1–4 years of relevant experience, including early full-time roles or researchStrong fundamentals in data structures, algorithms, and software designProficiency in Python and experience working with AI/ML frameworks (e.g., PyTorch, TensorFlow)Hands-on experience building, shipping, and maintaining software systemsFamiliarity with AI models, Transformers, and DiffusersExperience working with version control (Git) and collaborative development workflowsAbility to debug, optimize, and improve existing systemsStrong communication skills and ability to work independently in a fast-paced environmentBonusExperience with C++, CUDA, or AI inferenceContributions to open-source ML projectsWhy DeepInfraWork 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.