דרושים » אינטרנט ודיגיטל » לחברה ביטחונית ביקנעם- מהנדס /ת ++ C חזק /ה עם ניסיון בסביבת Real-Time

Were looking for an IoT Embedded Linux engineer to design, build, and own the software stack that powers our edge devices in the field. Youll craft resilient Linux-based systems (from bootloader to application), ensure secure and reliable connectivity to the cloud, and work closely with hardware, manufacturing, and backend teams to deliver production-ready devices at scale.
A Day In Your Life :
Own the embedded Linux platform: BSP, kernel configuration, device tree, bootloaders (e.g., U-Boot), systemd services, and startup/upgrade flows.
Develop user-space applications using object-oriented principles (C++/Go/Rust/Similar) to implement core device logic and features, leveraging available libraries and frameworks.
Build production images using Yocto or Buildroot, manage layers/recipes, and maintain reproducible builds for multiple hardware variants.
Implement secure OTA updates (e.g., Mender, RAUC, SWUpdate), with A/B partitions, rollback, and signing-targeting zero‑touch fleet upgrades.
Harden devices for security: filesystem permissions, sandboxing (e.g., AppArmor/SELinux), secure boot/TPM, key management, CVE tracking, and update policies.
Deliver robust connectivity: Ethernet/Wi‑Fi/Cellular (LTE), BLE gateway roles, MQTT/HTTPS, VPN/WireGuard; optimize reliability, roaming, and reconnection logic.
Instrument and debug in the field: journald, core dumps, remote shell, metrics/health checks; trace with strace/perf/tcpdump and diagnose with Wireshark.
Collaborate across disciplines: work with HW, manufacturing, QA, backend, and product to define requirements, provisioning flows, and factory test automation.
Raise the bar on quality: CI/CD for cross‑compilation, unit/integration tests, static analysis, reproducible builds, and fleet-safe release practices.

As an ML Software Engineer with a focus on low-level and CUDA-based optimizations, you will play a key role in shaping the design, performance, and scalability of machine learning inference systems. Youll work on deeply technical challenges at the intersection of GPU acceleration, systems architecture, and ML deployment.
Your expertise in CUDA, C/C++, and performance tuning will be crucial in enhancing runtime efficiency across heterogeneous computing environments. Youll collaborate with designers, researchers, and backend engineers to build production-grade ML pipelines that are optimized for latency, throughput, and memory use, contributing directly to the infrastructure powering next-generation AI products.This role is ideal for an engineer with strong systems-level thinking, deep familiarity with GPU internals, and a passion for pushing the boundaries of performance and efficiency in machine learning infrastructure.

Responsibilities
Design and implement highly optimized GPU-accelerated ML inference systems using CUDA and low-level parallelism techniques
Optimize memory, compute, and data flow to meet real-time or high-throughput constraints
Improve the performance, reliability, and observability of our inference backend across diverse compute targets (CPU/GPU)
Collaborate with cross-functional teams (including researchers, developers, and designers) to deliver efficient and scalable inference solutions
Contribute to ComfyUI and internal infrastructure to improve the usability and performance of model execution flows
Investigate performance bottlenecks at all levels of the stack-from Python to kernel-level execution
Navigate and enhance a large, complex, production-grade codebase
Drive innovation in low-level system design to support future ML workloads