Applying through our link may earn us a small commission — at no extra cost to you.
About this role
Your job is to find a real-world AI model failure within HW & electrical design. You will give the prompt, context, files etc. and run a preset range of models against the problem.
If you have several model failures in mind, you can submit several ones (as many as you want).
We will use your submitted data to benchmark a wide range of models, and measure how well they perform at embedded engineering tasks. For the brief:
1. Build an environment around a board or electrical system you have designed or debugged.
- Contents: schematics, layout excerpts or Gerbers, BOM (bill of materials), component datasheets, measurement data, and the design constraints (cost, size, temperature, standards).
- Give measurements as data files: scope captures as CSV, thermal readings as tables, EMC (electromagnetic compatibility) scans as frequency and level data. Images can go in as supporting material.
- Tools: ngspice or another SPICE (Simulation Program with Integrated Circuit Emphasis) simulator, KiCad, Python, PDF tools.
- Put in everything a hardware engineer on the project would have open. If a task depends on a file, the file has to be in the environment.
- Once saved, the environment appears under My environments on DOP. Write all your hardware tasks inside it.
2. Write tasks inside the environment. Five or more is ideal, and one is enough to start.
- Each task is a question.md plus the files it needs, built on a design decision or failure on that board.
- The model works through the documents and data, runs calculations or simulations, and writes answer.json with the faulty component or net, corrected component values, a part chosen from a shortlist you supply, and the computed margins (phase margin, derated current, junction temperature or similar).
- Your marking script checks each value within a tolerance you set and runs a SPICE netlist you supply with the proposed values.
- A strong task contains a part that looks right on paper and breaks one datasheet limit once temperature, ripple or enclosure airflow is applied.
- Supply your answer (it must score 1.0), the hidden marking script (0.0 to 1.0), and a naive answer that a competent engineer might give first, which must score below 0.3.
3. Example tasks
- Regulator oscillates at light load. Filter values after a layout change push conducted emissions over the limit. A component derates past its limit inside the enclosure.
4. Payment
- $300 per accepted task. A task is accepted when it passes review,.
About Hashlist
A credible, embedded-engineering-focused AI-data platform with genuine paid briefs ($300 per accepted submission) and a generous referral. It's a young, niche product with little public review history, so confirm payout terms as you go.
Trust score 7/10Read our Hashlist review →
Next steps
AITrainerGigs aggregates this listing from Hashlist.