Job Description :

We are seeking a talented and driven User-Mode Driver (UMD) / system software engineer to join our team and contribute to the host-side software stack for machine learning in the Next Gen Computational PCIe Flash Controller project.

In this role, you will be responsible for building high-performance user-space driver frameworks and runtime interfaces that enable efficient communication and data flow between applications and our device via the kernel driver.

You will work on key components including user-space APIs, command queues, memory orchestration, and multi-device management to enable scalable ML workloads.

User-Mode Driver Development :

- Architect and implement high-performance user-space driver libraries for Linux.

- This includes designing scalable abstractions for multi-device and multi-card systems, and enabling efficient interaction with PCIe devices through kernel interfaces.

Device Discovery & Topology Management :

- Design and implement mechanisms for PCIe device discovery, enumeration, and logical grouping across multiple endpoints and cards.

- Develop topology-aware abstractions for managing devices in complex multi-card and switched environments.

Custom Protocol Design :

- Design and implement a custom, NVMe-like command and control protocol in user space.

- You'll be responsible for the host-side orchestration, including :

1. Command Queues : Manage submission and completion queue abstractions and request tracking.

2. Command Orchestration : Implement tag-based request management, async/sync execution, and callback handling.

3. Event Handling : Design event-driven completion handling using poll/eventfd mechanisms.

User ? Kernel Interface Integration :

- Develop efficient interaction with the kernel driver using ioctl, mmap, and event mechanisms.

- Translate high-level runtime requests into kernel-mediated operations while maintaining performance and isolation.

Memory & Dataflow Management :

- Design user-space data movement strategies, including DMA buffer lifecycle management, memory pinning workflows, and zero-copy data paths for efficient host-device communication.

Multi-Application Support :

- Enable concurrent multi-process access to devices using per-file descriptor resource management, ensuring isolation, scalability, and robustness across workloads.

Collaboration :

- Work closely with runtime, kernel driver, firmware, and hardware teams to define clean interfaces and deliver a cohesive, high-performance end-to-end solution.

Qualifications :

- Experience : 8+ years in system software or runtime development.

- User-Space Systems Expertise : Strong experience building user-space drivers, runtime libraries, or high-performance system software interacting with kernel interfaces (ioctl, mmap, eventfd).

- Protocol Knowledge : Deep understanding of PCIe and NVMe-like queue models, including submission/completion queues, descriptors, and asynchronous execution patterns.

- Low-Level Proficiency : Mastery of C/C++ and strong understanding of memory management, concurrency, and virtual memory.

- System Architecture : Experience designing scalable APIs and abstractions for complex hardware/software systems.

- Problem-Solving : Exceptional debugging and analytical skills across user-space, kernel, and hardware boundaries.

- Education : Bachelor's or Master's degree in Computer Science, Electrical Engineering, or a related field.