PhD Position in Memory-Centric NPU Architectures and Emerging Memories for Edge AI at NXP (Hamburg, Germany)

Job Description

NXP Semiconductors is offering a PhD position in AI hardware at its Hamburg site, researching memory-centric neural processing unit (NPU) architectures and emerging embedded memories for edge AI and embedded generative AI (requisition R-10064337).

At a glance

• Position: PhD candidate (industrial PhD)
• Where: NXP, Hamburg, Germany
• Contract: Part time (80%), limited to 3 years
• Pay: Not stated in the posting
• Field: Computer architecture, AI accelerators, semiconductor memory
• Apply: open until filled (re-checked 17 October 2026)

About the PhD in AI hardware at NXP

• Research next-generation NPU subsystem architectures that put memory at the centre of the design
• Evaluate and model emerging embedded memories such as eDRAM and gain-cell RAM (GCRAM) for AI accelerators, including their effect on power, area, reliability and scalability
• Develop hardware/software co-optimisation techniques for running AI workloads efficiently on NPU-based systems
• Build architecture modelling, simulation and performance-power-area (PPA) evaluation frameworks for design-space exploration
• Benchmark real workloads including CNNs, Transformers, LLMs, vision-language models and multimodal systems
• Publish results at conferences and in journals, working alongside NXP experts in semiconductor design, system architecture and embedded AI

NXP frames the project around a simple observation: as AI models grow, moving and storing data, rather than raw compute, is becoming the main bottleneck in accelerators. The research sits between computer architecture, semiconductor memory systems, machine learning and embedded systems, and NXP says it is meant to feed into future generations of its edge AI processors.

Why this role matters

Most PhD students in computer architecture work with simulators and public benchmarks alone. Here the candidate gets access to production NPU architectures, NXP’s internal simulation frameworks and memory technologies under evaluation for future products, so the thesis can be tested against real design constraints. Edge AI hardware is also one of the busiest hiring areas in the chip industry, which makes this a strong route into semiconductor R&D.

What NXP is looking for

• A master’s degree in electrical engineering, computer engineering, computer science, microelectronics, embedded systems or a related field
• A strong background in one or more of: computer architecture, digital design, embedded systems, semiconductor memory systems, AI accelerators and NPUs, or hardware/software co-design
• Programming experience in Python and C/C++
• Knowledge of architecture simulation, performance modelling or hardware design methods
• Very good written and spoken English

Nice to have

• AI accelerator or NPU architecture experience
• RTL development in Verilog, SystemVerilog or VHDL, and FPGA prototyping
• Experience with computer architecture simulators and memory-hierarchy optimisation
• Familiarity with eDRAM, GCRAM, MRAM, ReRAM or CXL-based memory systems

Pay and location

NXP does not state a salary in the posting. The contract is part time at 80% and limited to three years, based in Hamburg, Germany. The posting also notes that the successful candidate may handle security-related tasks within the scope of security certifications.

How to apply

Apply through the official NXP job posting. NXP’s posting does not give a closing date, so the role is open until filled; ResearchJobs.in will re-check this listing on 17 October 2026. Check the posting for location and work-authorisation details before you apply.

See all our artificial intelligence jobs, or browse more research jobs on ResearchJobs.in.