Staff Research Scientist, AI-Hardware Co-Design

Job Title

Staff Research Scientist, AI-Hardware Co-Design

Role Summary

Architect AI-hardware co-design solutions to enable efficient edge and embedded intelligent systems. Work in ADI's Algorithmic Solutions Group (Analog Garage, Boston) to translate research into validated proofs-of-concept and define compute strategies across MCUs to custom accelerators.

Partner with business leads, researchers, and hardware teams to deliver system-level architectures that optimize algorithms, memory, and dataflow for power- and area-constrained deployments.

Experience Level

Senior — requires a PhD-level technical background and practical experience applying computer architecture principles to real-world engineering constraints; the posting specifies 3+ years of industry experience.

Responsibilities

Main responsibilities include:

• Collaborate with business and domain experts to define high-impact system problems and technical requirements.
• Lead research-to-product efforts: architect solutions, run feasibility studies, and deliver validated proofs-of-concept.
• Perform feasibility analysis using high-fidelity simulation and modeling to quantify memory, dataflow, and precision trade-offs.
• Drive system-level co-design of algorithms and hardware, selecting compute substrates and adapting neural architectures for hardware constraints.
• Provide technical leadership: survey AI-hardware advances, mentor staff, and guide architectural decisions.

Requirements

Must-have skills and experience:

• Proven system-level hardware architecture experience focused on data movement, memory hierarchy, and energy-per-operation optimization.
• Experience with high-fidelity or cycle-accurate simulation and performance modeling.
• Hardware-aware ML expertise: mapping computational graphs to hardware, dataflow, tiling, and quantization (INT8, mixed-precision).
• Practical experience with modern ML frameworks (PyTorch, JAX) and training/fine-tuning models to validate architectural hypotheses.
• Ability to translate research ideas into deployable prototypes across a range of compute substrates (MCUs to custom accelerators).
• Willingness to travel up to 10% and work standard daytime shift (1st shift).

Nice-to-have:

• Proven silicon execution (SoC or accelerator tape-out) and familiarity with physical-design constraints.
• DSP and signal-processing background (Fourier analysis, sampling, noise-floor considerations).
• Hands-on RTL or hardware construction language experience (Verilog/SystemVerilog, Chisel, PyMTL).
• Strong publication record in top conferences or journals.

Education Requirements

PhD in Computer Architecture, Integrated Circuit Design for AI workloads, or a closely related field is required; the posting also specifies 3+ years of relevant industry experience. No equivalent-degree substitution was stated.

About the Company

Company: Analog Devices

Headquarters: Norwood, Massachusetts, USA

Analog Devices is a leading global semiconductor company that bridges the physical and digital worlds, enabling breakthroughs at the Intelligent Edge. With a focus on innovation, ADI develops solutions that drive advancements in digitized factories, mobility, and digital healthcare. The company employs around 24,000 people globally and reported revenues exceeding $9 billion in FY24, creating technologies that transform lives across various sectors.