Tasks
If you're excited by the idea of building technologies that go beyond today's AI accelerators and helping define the future of computing, we'd love to hear from you. We are looking for a Compiler Engineer to join the team developing Intel's next-generation neuromorphic AI software platform. You'll play a key role in creating a production-grade SDK that powers edge and robotics applications on novel AI hardware. Working across the software stack, you'll collaborate closely with compiler, hardware, runtime, systems, and application engineers to build highly optimized tools that unlock the full potential of Intel's neuromorphic technology. This is an opportunity to solve fundamentally new computing challenges while helping bring breakthrough AI technology from research into real-world deployment.
•Design and develop next-generation compiler technologies for autonomous and event-driven AI workloads.
•Solve complex compilation challenges for massively parallel spatial architectures, including:
•Graph partitioning
•Placement and routing
•Scheduling
•Automatic kernel selection
•Distributed memory allocation
•Build and enhance compiler infrastructure using LLVM and MLIR frameworks.
•Develop domain-specific languages and high-performance kernels to maximize application efficiency.
•Prototype and demonstrate emerging AI workloads on neuromorphic accelerators.
•Partner with cross-functional teams across hardware, runtime, systems, and AI applications.
•Drive software quality through code reviews, automated testing, benchmarking, and documentation.
•Contribute to the evolution of modern AI software engineering practices and tools.
Requirements
•Bachelor's degree with 5+ years of experience, Master's degree with 3+ years of experience, or PhD in: Computer Science, Computer Engineering, Electrical Engineering, Applied Mathematics, Physics, or a related discipline.
•Strong professional experience developing software in C++ and Python.
•Hands-on experience with LLVM and/or MLIR compiler frameworks.
•Solid understanding of modern software engineering practices, including:
•Git version control
•Code reviews
•Testing and debugging
•CI/CD workflows
•Experience working with AI frameworks such as PyTorch, TensorFlow, or JAX.
•Strong English communication skills.
•Modern AI compiler frameworks and deployment tools such as: Triton, IREE, TVM, ONNX, OpenVINO.
•AI accelerators, neuromorphic hardware, or heterogeneous computing systems.
•Parallel programming and performance optimization (CUDA, OpenCL, multithreading).
•AI model development across areas such as: Computer Vision, NLP, Large Language Models (LLMs), Vision Language Models (VLMs), Signal Processing.
•Optimization algorithms including: Integer Linear Programming (ILP), SAT/SMT Solvers, Graph Partitioning.
•Performance analysis and profiling tools such as Intel VTune, Nsight, cProfile, or VizTracer.
•Ability to thrive in a fast-moving environment where priorities evolve as products mature.
Conditions
As part of Intel's CTO organization, you'll be joining a highly collaborative team that has pioneered multiple generations of neuromorphic computing technology and is now focused on bringing these innovations to market. You'll have the opportunity to:
•Work on breakthrough AI hardware and software technologies
•Influence compiler architecture from the ground up
•Collaborate with world-class researchers and engineers
•Solve challenges that don't exist in conventional computing environments
•Help define the future of edge AI, robotics, and autonomous systems
Please note this is a temporary position from 12 up to 24 months. Job Type: Intel Contract Employee. Shift: Shift 1 (Germany). Primary Location: Germany, Munich.
Annual Salary Range for this job which could be performed in Germany is: 79,130.00 € - €145,000.00. The compensation range displayed in this posting reflects the minimum and maximum target compensation for this position. Within this range, individual pay is determined by job related skills, experience, and relevant education, training. As part of our total compensation approach, the final offer may include additional pay components and benefits.
This role will be eligible for the hybrid work model, which allows employees to split their time between working on-site at their assigned Intel site and off-site.
