EmergingAI accelerators and hardware co-design

Neuromorphic Computing Researcher

Also called Neuromorphic AI Scientist

A neuromorphic computing researcher tests whether event-driven, brain-inspired computation can beat conventional hardware on a real task. The answer shapes whether a company invests in unusual chips or stays with what it has.

What they do

The work starts with a task that might suit sparse, event-driven computation, such as streaming sensor data or low-power inference. The researcher builds a spiking model or event-driven design, then simulates it or prototypes it in hardware description code. Next come the baselines. The same task is run on GPUs or other standard hardware, and the two are compared on accuracy, latency and energy. They profile workloads, find where the hardware assumptions break, and write up what held and what did not. Much of the day is simulation, debugging and reading results sceptically.

What a strong hire delivers

In the first months, a strong hire delivers a clear shortlist of tasks where event-driven computation might help and where it will not. They produce a working simulation or small prototype with honest baseline comparisons. They document the assumptions about hardware that the results depend on. The company ends up with a defensible view on whether to go further, and a reusable test setup for the next idea.

How you can tell they are good

Ask them to walk through one comparison they ran against a conventional baseline. A strong candidate explains why the baseline was fair, what the energy figure included and excluded, and where the approach failed. They separate simulated results from measured ones. They can describe how a spiking model maps onto event-driven hardware, and they are comfortable saying the idea does not suit a given task.

Why it is hard to fill

Almost nobody holds this title in industry today. The work often sits inside chip architecture, research or advanced development teams under other names. The skill mix is odd: spiking models, computer architecture and practical simulation rarely live in one person. Many candidates are strong on the neuroscience side or the chip side, but not both. Academic profiles are common. Those who have also faced fair baseline comparisons are scarcer.

Where to find them

Look in computer architecture groups, electrical engineering departments and chip design teams that have explored event-driven or low-power designs. Research labs and university groups working on spiking networks are a source, as are engineers in sensor and edge device companies. Typical titles include hardware researcher, architecture engineer, RTL designer, computational neuroscientist with hardware experience, and research scientist in accelerators.

Indicative pay

Not enough published evidence yet to give a fair range for this role, which is common for work this new. We benchmark it for you as part of a search.

Interview questions for a Neuromorphic Computing Researcher

  1. Describe a task where you compared an event-driven approach with a conventional baseline. What did you find?

    A strong answer names the task, the baseline and the metrics, and admits where the event-driven approach lost. Worry if they only report wins, use vague energy claims, or cannot explain how the baseline was tuned.

  2. How would you decide whether a workload suits spiking computation at all?

    Look for talk of sparsity, temporal structure, streaming input and latency or power limits. A good answer includes reasons to reject a workload. Worry if they treat brain-inspired as automatically better.

4 more questions, with what a strong answer covers, are in the Role Kit.

Job description you can post

We are exploring whether event-driven, brain-inspired computation can do useful work at lower energy than conventional hardware. We need a researcher who can build prototypes and simulations, compare them fairly with standard baselines, and tell us plainly what the results mean for our hardware choices.

What you will do

  • Identify tasks where event-driven computation might offer real advantages
  • Build spiking models and event-driven designs in simulation or RTL
  • Run fair comparisons against GPU and other conventional baselines
  • Profile workloads and measure energy, latency and accuracy
  • Document the hardware assumptions behind each result
  • Report limits and failures as clearly as successes
  • Work with architecture and software colleagues on next steps

What you will bring

  • Demonstrated work on spiking models or event-driven hardware
  • Experience with computer architecture, chip design or similar
  • Hands-on use of RTL, hardware simulators and EDA tools
  • Solid grounding in linear algebra and optimisation
  • Experience with GPU programming for baseline comparisons
  • A record of honest, well-documented benchmarking

Nice to have

  • Experience with workload profiling on real systems
  • Work with digital twins or large-scale simulation
  • Published or shared prototypes or open research code

Free to use and adapt. If it saves you time, a link back to this page is appreciated.

Skills that matter

  • Hardware and computer architectureAdvancedDesign computing structures and hardware interfaces
  • GPU programmingAdvancedOptimise parallel accelerator kernels
  • Linear algebra and optimisationWorkingReason about matrix operations and objective functions
  • Simulation and digital twinsWorkingBuild useful virtual representations of environments

Other roles in aI accelerators and hardware co-design

Hiring nowAI Accelerator ArchitectAn AI Accelerator Architect decides how a chip or compute system should be built for specific training or inference workloads. Their choices set the…Hiring nowAI Hardware Verification EngineerAn AI Hardware Verification Engineer proves that accelerator logic and its interfaces behave correctly before silicon is committed. Escaped defects…Hiring nowHardware-Software Co-Design EngineerA Hardware-Software Co-Design Engineer shapes model software and chip interfaces together, so neither is tuned in isolation. For an AI company, that…

Related roles in other families

Hiring nowAI Inference Compiler EngineerAI compilers, kernels and runtime systemsAn AI Inference Compiler Engineer makes trained models run faster and cheaper on real hardware. They change how model computation is compiled and…Hiring nowGPU Kernel EngineerAI compilers, kernels and runtime systemsA GPU Kernel Engineer writes and tunes the low-level code that runs model operations on accelerators. Faster, correct kernels cut compute cost and…Hiring nowML Runtime EngineerAI compilers, kernels and runtime systemsAn ML Runtime Engineer builds the scheduling, memory and execution layer that runs models on real hardware. Their work decides whether a model…EmergingAI Performance Portability EngineerAI compilers, kernels and runtime systemsAn AI Performance Portability Engineer keeps models fast and accurate across different hardware. They cut dependence on one chip or vendor, which…

How we wrote this

Role definitions are our own editorial work, checked against occupational classifications, standards, research and employer pages. Titles vary by company, and this is a description of the work, not a job advert.

← AI accelerators and hardware co-designAll new job families

Start a search

Hiring a Neuromorphic Computing Researcher?

Tell us the work. We find the people already doing it, whatever their job title says, and you meet them already interviewed for your role.