Senior Machine Learning Engineer - AI Systems & Frameworks

We are seeking a senior engineer to join our high-performance team, which partners with leading AI chip companies to deliver cutting-edge software that enables end-users to run Vision and Generative AI inference workloads efficiently on custom accelerators.

As a Senior Machine Learning Engineer, you will be a key technical member of the team, working in a hands-on role to contribute to the design and development of frameworks, APIs, and runtime integrations that enable AI models to run seamlessly on next-generation hardware. You will also help shape technical direction, mentor junior engineers, and collaborate closely with the client's compiler/runtime and hardware architecture teams.

This is not a traditional applied ML role. Instead, it requires deep software engineering expertise with strong exposure to AI/ML systems, ideal for someone who thrives in systems programming and performance optimization, and wants to pivot into the AI/ML domain while continuing to build on their proven experience in delivering robust, high-quality software. In this role, you will directly contribute to enabling large-scale AI workloads on custom hardware.

What you'll do

• Define and implement software architecture and design patterns to ensure frameworks and applications are scalable, maintainable, and reusable.

• Architect and develop Python/C++ frameworks for integrating ML models with custom runtimes.

• Design and implement high-performance APIs, bindings, and libraries to support inference of Vision and Generative AI models.

• Build and maintain Model Zoo, loaders, and optimization workflows to simplify model deployment.

• Profile, debug, and optimize performance-critical paths in runtime and framework layers.

• Develop real-time pipelines and applications using GStreamer, OpenCV, and other multimedia/ML frameworks.

• Collaborate with compiler/runtime teams to ensure smooth integration of graph-level and operator optimizations.

• Mentor and guide junior engineers; enforce software engineering best practices across design, testing, CI/CD, and code reviews.

• Own end-to-end delivery of software components: define scope, set timelines, and drive execution.

Do you have a Master's degree?, * 5-7+ years of professional experience in software engineering, ideally in systems programming or performance-critical applications.

• Strong programming expertise in C++ (C++11/14/17) and Python.

• Experience with C++/Python bindings (e.g., pybind11, SWIG).

• Strong fundamentals in:

• Data structures and algorithms

• Concurrency, threading, and synchronization

• Memory management, caching, and performance profiling

• Networking and streaming systems

• Exposure to ML frameworks (PyTorch, TensorFlow, ONNX Runtime) and how they interface with hardware runtimes.

• Experience building frameworks, SDKs, or toolchains used by other developers or customers.

Bonus Points

• Hands-on experience deploying vision or Generative AI models (transformers, diffusion models, LLM inference).

• Experience with multimedia/vision pipelines (e.g., GStreamer plugin development).

• Contributions to open-source ML systems projects (e.g., Hugging Face, ONNX Runtime, TensorRT).

• Prior experience in a technical lead or client-facing role.