1 день назад
Senior Software Compute Architect (AI/Compiler)
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior Software Compute Architect (AI/Compiler): Defining the software architecture, programming model, compiler, runtime, and workload-placement mechanisms for a hybrid electronic/photonic compute engine with an accent on heterogeneous computing and AI workload performance. Focus on designing hardware/software interfaces, modeling transformer training and inference, and prototyping kernels, libraries, and runtime concepts for scalable execution across compute paths.
Location: On-site in Aachen, Germany
Company
develops graphene photonic solutions that connect chips through high-throughput, low-delay computing networks, combining electronic computing with photonic communication.
What you will do
- Define the programming model, instruction abstractions, and software interfaces for hybrid electronic/photonic compute capabilities.
- Own the compiler, runtime, and library strategy for mapping workloads and kernels to optimal compute paths.
- Develop performance models for AI workloads, including transformer training and inference, to evaluate hardware/software configurations.
- Collaborate with hardware architects on interface contracts, telemetry, control mechanisms, and hardware/software co-design.
- Define software and firmware strategies for scale-up and scale-out execution across nodes, packages, and systems.
- Prototype kernels, libraries, and runtime concepts against real AI benchmarks.
Requirements
- Bachelor’s or Master’s degree in Computer Science, Electrical Engineering, Computer Engineering, or a related field, or equivalent experience.
- 5+ years of experience building compiler, runtime, or systems software for accelerated, heterogeneous, or specialized compute platforms.
- Strong compiler architecture experience with LLVM, MLIR, or comparable infrastructure targeting custom accelerators or heterogeneous hardware.
- Experience defining instruction sets, programming models, or hardware/software abstractions for novel compute architectures.
- Experience optimizing kernels and libraries for AI workloads and modeling LLM training and inference across hardware architectures.
- Experience with LLVM/MLIR, Triton, CUTLASS-style DSLs, PyTorch, JAX, Python, C++, and profiling or performance-modeling tools.
Nice to have
- Familiarity with photonic or optical compute concepts and their impact on compiler and runtime strategies.
- Experience with CUDA, ROCm, Triton, oneAPI, or custom accelerator software stacks.
- Contributions to open compiler or runtime ecosystems, or experience with firmware-level scheduling and accelerator control-plane design.
Culture & Benefits
- Flexible, human-centric work culture focused on work-life harmony.
- Autonomy and continuous professional and personal development.
- Benefits package including insurance, pension, and virtual stock options.
- Open, inclusive, and collaborative environment focused on innovation and growth.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →
Похожие вакансии
24 часа назад
LLVM / MLIR Compiler Architect - Photonic Computing
Anthropic
4 дня назад
Applied AI Architect, Industries (AI)
7 часов назад
Principle Engineer - Architecture (m/w/d)
9 часов назад
Cloud Architect (AWS)
1 день назад
Native Processing Server Architect (Photonic AI)
Cohere
1 день назад