Own the GPU software stack on every Runware node: the firmware, the kernel and NVIDIA driver, the CUDA runtime and libraries, the container runtime, and the way Kubernetes and our inference services see and share a GPU.
Responsibilities
Own the GPU software baseline.
Qualify every driver and CUDA release.
Take GPU failures to root cause: Xid errors, CUDA "unknown error", cuBLAS handle failures, out-of-memory and fragmentation, GPUs that fall off the bus.
Build GPU acceptance and diagnostics: the burn-in, DCGM diagnostics, memory and interconnect tests and real-workload tests that gate every node and rack before it serves traffic, and the reports customers receive at handover.
Make GPU health visible and self-healing. Pull telemetry from DCGM, the driver, the kernel log and the BMC into one trusted view, classify faults, and automate the drain, reset and replacement paths.
Requirements
Nice to have: Blackwell-generation hardware (B200, GB200/GB300 NVL72)
Applied research focused on advancing efficiency across the AI stack, spanning models, ML frameworks, cloud infrastructure, and hardware, driving mid- and long-term product innovation.
Compensation
The typical base pay range for this role across the U.S. is USD $119,800 - $234,700 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $160,200 - $261,000 per year.
Responsibilities
Formulate, develop, and evaluate new algorithmic and system-level approaches for end-to-end AI serving
Design and experimentally evaluate endpoint configuration and execution policies, including batching, routing, and scheduling strategies
Perform hardware- and kernel-aware optimization by collaborating closely with model, kernel, compiler, and hardware teams
Build and benchmark experimental prototypes and large-scale measurements to validate research ideas and drive them toward production readiness
Publish research results, file patents, and, where appropriate, contribute to open-source systems and serving frameworks
Requirements
Doctorate in relevant field
Master's Degree in relevant field
Bachelor's Degree in relevant field
Nice to have: Inference systems design and optimization
The Windows Device Engineer builds the endpoint agent that sits closest to the user. It runs on every Windows machine, sees the traffic, makes decisions locally, and never gets in the way.
Join the IVI Intelligence Lab and help build AI features that ship in Ford vehicles. You will work across the stack, from cloud training and serving to on-device inference, in computer vision, speech, personalization, and language models.
Compensation
The expected annual salary range for this Ford of Canada position is $96,000.00 - $146,000.00 and individuals may be eligible to participate in our Annual Compensation bonus program.
Responsibilities
Ship on-device AI: Deploy and optimize models on the vehicle SoC using quantization, pruning, and distillation, meeting strict latency, memory, power, and thermal budgets across CPU, GPU, and NPU acceleration.
Integrate with the platform: Embed inference in the Android Automotive OS software stack through system services and native (C++ and JNI) code, working against camera, audio, and vehicle signal interfaces.
Build the data flywheel: Construct cloud training pipelines and MLOps practices that turn vehicle data, under strict privacy controls, into continuously improving models: ingestion, curation, training, evaluation, registries, and drift monitoring.
Personalize the vehicle: Develop vision and speech models that recognize who is in the car, so the vehicle can prepare their profile, settings, and preferred one-tap actions, as convenience features on a secure-by-design data path with automatic fallback to the device credential (PIN, pattern, or password).
Predict and adapt: Build context engines and predictive models that learn driver behaviour, curate useful next actions before they are requested, and adapt interface surfaces and drive coaching to what perception detects inside and around the vehicle.
The typical base pay range for this role across the U.S. is USD $102,100 - $202,200 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $133,800 - $219,200 per year.
Responsibilities
Design and develop novel quantization and numerics algorithms to enable efficient deployment of LLM inference and training in Microsoft’s Azure production environments.
Drive software development and model optimization tooling proof-of-concept effort to streamline deployment of quantized models.
Analyze performance bottlenecks in quantized state-of-the-art LLM architectures and drive performance improvements.
Prototype and evaluate emerging low-precision data formats through proof-of-concept implementations on novel hardware accelerator SDK.
Co-design model architecture optimized for low-precision deployment in close collaboration with companywide AI/ML teams.
Requirements
Bachelor's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field
Master's Degree in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field
Doctorate in Statistics, Econometrics, Computer Science, Electrical or Computer Engineering, or related field
Nice to have: publications (patents, peer-reviewed academic papers)
Розробка гібридних алгоритмів (CV + ML) для виробництва БпЛА, включаючи підбір апаратної бази, збір та розмітку даних, навчання та оптимізацію моделей для інференсу в реальному часі.