Ai Embedded Software Engineer jobs at Intel in Romania, Timișoara

Responsibilities:

• Design, implement, and optimize compiler features for Intel NPU architectures, ensuring high performance and efficient code generation.
• Enable and optimize machine learning models—including LLMs—for deployment on Intel NPUs, focusing on quantization, dynamic execution, and hardware-specific acceleration.
• Collaborate with other teams to productionize new models and support emerging AI workloads.
• Develop and maintain model conversion, quantization, and deployment pipelines, ensuring correctness, reproducibility, and compliance with Intel’s standards.
• Benchmark, profile, and debug models and software components to identify and resolve performance bottlenecks.
• Stay current with the latest advancements in compilers, model optimization, quantization, and LLM research, and integrate best practices into the NPU software stack.
• Write clear technical documentation and provide support to internal and external users.

• Bachelor’s, Master’s, or Ph.D. in Computer Science, Electrical Engineering , or related field.
• Proven expertise in C/C++ with strong software design and optimization skills.
• Solid understanding of AI model optimization techniques such as quantization, pruning, and distillation.
• Familiarity with large language models and their deployment requirements.
• Knowledge of computer architecture , hardware acceleration, and low-level performance tuning .
• Proficiency with Linux environments , virtualization, and CI/CD workflows.
• Strong analytical, problem-solving, and cross-team collaboration skills in fast-moving technical settings.
• Experience with modern compiler infrastructures (e.g., LLVM, MLIR ) or code generation for custom accelerators is a plus.
• Hands-on experience with AI frameworks (OpenVINO, TensorFlow, PyTorch, ONNX), Python , and performance tools for NPUs, GPUs, or FPGAs is a plus.
• Experience developing dynamic execution or runtime systems that handle variable input sizes and adaptive behavior is a plus.
• Familiarity with collaborative tools (GitHub, Jira) and open-source contribution practices is a plus.

Key Responsibilities:

• As an AI Embedded Software Engineer, you'll be an integral part of a dynamic team developing NPU IP Pre-Silicon Simulation software models.

• Collaborate with multi-disciplinary engineers and architects to model future Intel NPU hardware IP, crafting software virtual platforms for early software bring-up and robust hardware validation environments.

• Gain a broad understanding of how HW-based acceleration products are built and learn why these products are the real engine behind the AI revolution.

What Awaits You on Your Intel Journey:

• Innovative Environment: Immerse yourself in cutting-edge virtual platform modelling technology, using platforms such as Intel Simics and state-of-the-art UVM hardware validation methodologies.

• Rapid Skill Enhancement: Expand your existing expertise through advanced software engineering techniques and embedded software development practices.

• Collaborative Excellence: Work alongside RTL designers, validation engineers, and SW/FW and OS driver developers to deliver world-class products

• Architectural Influence: Grow your AI development skills and contribute to architectural and technical deliverables while adhering to sound software engineering principles.

• Career Growth: We will invest in you, helping you to sustain and reach your long-term career goals focusing both on hard and soft skill development.

Minimum Qualifications:

• Master/Bachelor of Science in Computer Science, Electrical Engineering, or relevant technologydegree/qualificationwith 3+ years of applicable industry experience.

• Software Proficiency: Strong background in object-oriented programming, C++.

• Linux Software Development: Development and debug experience is a must.

• AI Fundamentals: Basic understanding of underlying principles such as dot product (multiply and accumulate), activation functions, convolution, etc., and how they relate to, and enable, AI network topologies.

• Experience with Python, Git for source code management and CI/CD and automated software/hardware regression testing are highly advantageous.

• Familiarity with SoC Architecture: System-level understanding of data flows and memory management, including simulation of HW components and functions such as registers, data/memory interfaces, MMUs, CPUs, DSPs, NoCs, interrupts, and CPR (clock, power, reset).

Preferred Qualifications:

• Embedded Hardware Design: Experience withVHDL/Verilog/SystemVerilogfor simulation and synthesis is highly advantageous.

• Virtual Platform Modelling: Hands-on experience with Intel Simics or similar virtual platform modelling and simulation environments.

• Multithreaded Application Development: Expertise in C/C++.

• Experience with UVM: For hardware verification.

• Hardware Validation: experience with SystemVerilog and UVM for pre-silicon hardware validation

• Embedded SW, Firmware, and/or System Validation: Debug and signoff experience.

• Numerics and AI Data Processing: Understanding of floating point datatypes, type conversion, commutativity, and precision in the context of AI data processing structures such as tensors and blobs.

• Requirements listed would be obtained through a combination of industry-relevant job experience, internship experiences, and/orschoolwork/classes/research.On-the-job training will be given in these areas as you take the next step in your career with our team.