Software Engineer - AI Systems & Frameworks

We are seeking a Software Engineer to join our high-performance team collaborating with leading AI chip companies. Our work focuses on developing software that enables users to run Vision and Generative AI inference workloads efficiently on custom accelerators.

This is a hands-on engineering role where you will contribute to the development of frameworks, APIs, and runtime integrations that power AI models on next-generation hardware. You will work alongside senior engineers and coordinate with compiler/runtime and hardware architecture teams.

This is not a traditional applied ML position. It suits someone who wants to build a strong foundation in AI/ML systems, performance optimization, and software engineering, while contributing to production-grade AI enablement., * Assist in implementing scalable software architecture and design patterns.

• Help develop Python/C++ frameworks that integrate ML models with custom runtimes.
• Contribute to building high-performance APIs, bindings, and libraries for Vision and Generative AI inference.
• Support Model Zoo maintenance, model loaders, and optimization workflows for easier deployment.
• Profile, debug, and optimize performance-critical sections in framework and runtime layers.
• Contribute to real-time pipelines using GStreamer, OpenCV, and related frameworks.
• Collaborate with compiler/runtime teams on graph-level and operator optimizations.
• Apply best practices in design, testing, CI/CD, and code reviews.
• Participate in end-to-end software delivery, including defining scope and meeting project timelines.

• 2 - 3 years of professional or internship experience in software engineering, preferably in systems programming or performance-related domains.
• Proficiency in C++ (C++11/14) and Python.
• Familiarity with C++/Python bindings such as pybind11 or SWIG.
• Strong understanding of Data structures and algorithms; Concurrency, threading, and synchronization; Memory management, caching, and performance profiling; Networking and streaming systems.
• Some exposure to ML frameworks such as PyTorch, TensorFlow, or ONNX Runtime and their integration with hardware runtimes.
• Interest in building frameworks, SDKs, or toolchains used by other developers.

Bonus Points

• Experience working with Vision or Generative AI models such as transformers, diffusion models, or LLM inference.
• Familiarity with multimedia and vision pipelines (for example, GStreamer).
• Contributions to open-source projects or personal ML systems experiments (for example, ONNX Runtime or Hugging Face).
• Strong motivation to learn and work in a collaborative technical environment., * Are you legally authorized to work in EU?

• Work with a world-class chip company on state-of-the-art AI systems.
• Build a solid foundation in AI software and performance engineering.
• Continuous exposure to Vision and Generative AI workloads without repetitive applied ML tasks.
• Grow into more advanced technical roles across multiple AI projects.

Job Types: Full-time, Permanent