Fully Remote and Freelance Project- 8-10 hours per week expected as a minimum

Opportunity for experienced electrical engineers to evaluate how frontier AI models handle real engineering work:

This is not a traditional electrical engineering role. You will be helping build better AI by putting your knowledge to work in a structured, flexible, fully remote environment.

The work is long form and self directed, and clear written reasoning matters as much as technical depth

About the Role:

• Evaluate how frontier AI models handle real engineering work: specifying a circuit, stabilizing a control loop, closing a link budget, sizing a power stage, debugging a signal chain.
• The models can already talk fluently about electronics; what they cannot yet do reliably is the actual work.
• You bring the judgment you have built over years of designing, debugging, and shipping hardware. We bring the engineering problems the models cannot yet solve on their own.
• This is a new and growing area for our company, focused on teaching AI to reason correctly about circuits, systems, and physical constraints.
• Design challenging, realistic tasks drawn from your own practice, run them through frontier AI models, and evaluate what comes back against a professional standard.
• Your engineering judgment, your standard for what counts as a correct answer, and the written rationale behind them become the signal that shapes the next generation of engineering tools.
• You will work with realistic professional files, the kind a practitioner in your field actually handles, which you assemble yourself. Some tasks are compact, built around a handful of files; others are larger scenarios that take several days to build.
• In every case the goal is the same: a task a competent professional in your field would complete correctly and a frontier model currently gets wrong.

Responsibilities

• Design challenging, realistic engineering problems drawn from your own professional expertise: a circuit to specify, a control loop to stabilize, a link budget to close, a power stage to size, a signal chain to debug, along with the supporting files an engineer would need (schematics, simulation setups, datasheets, board files, measurement data), which you author yourself.
• Run those problems through frontier AI models and evaluate the deliverable they produce against the standard you would hold a colleague to.
• Compare two model versions on identical prompts and supporting material, decide which performed better, and document where each fell short.
• Critique model-generated derivations, schematics, component selections, simulation setups, and design calculations, and write detailed grading rubrics plus the reasoning behind your judgment.
• Flag concrete failures with evidence: unstated or wrong assumptions, sign and unit errors, unphysical results, invalid component or topology choices, misapplied approximations, fabricated datasheet values, misread schematics and plots, and off-brief interpretation of the ask.
• Contribute across analog, RF and mixed-signal circuits, electromagnetics, microwaves and antennas, control and systems, electronic devices and materials, signal processing, photonics and optoelectronics, and electric power and energy systems, and review and refine tasks built by other engineers.

Qualifications

• Several years of industry experience in circuit or electronics engineering; 5 or more years is a plus.
• Any specialty: analog, RF and mixed-signal, power electronics, embedded and controls, signal processing, electromagnetics and antennas, photonics and optoelectronics, or electric power and energy systems.
• Background in electrical engineering, electronics engineering, or a closely related discipline.
• Strong command of circuit analysis and design tradeoffs, and the ability to defend component-level and system-level decisions.
• Fluency in the tools of your specialty: circuit simulation (SPICE and similar), schematic capture and PCB tools, lab instruments, and MATLAB or Python for engineering analysis.
• Meticulous: you check your own work and enjoy finding the edge case that breaks an assumption.

Process:

Assessment- 2-3 hours (unpaid)

For more information and how to sign up, please get in touch