🤫husshhussh
🤫husshhusshOnePuppy
AI research · H37

Privacy Preserving Machine Learning Scientist

Find ways to learn from useful signals without casually exposing the people behind them. You will test privacy methods against explicit adversaries.

See what is open todayAll roles

Not open yet: Research program

This work starts when that stage arrives, so there is no application to submit today and we will not pretend otherwise. What is written below is what the role is for and what would make somebody right for it, published early on purpose so you can decide whether it is worth watching.

The work

What this person actually does

Research differential privacy, federated learning, secure aggregation or related techniques where they fit the problem. Measure privacy-utility tradeoffs and leakage from updates or outputs. Work with cryptography and product teams on deployable guarantees and understandable consent.

The milestone

What it looks like when it is working

In your first 90 days, deliver a threat model, a reproduced baseline and a privacy evaluation with clearly stated assumptions.

Evidence

What would show us you can do it

Bring rigorous privacy or ML research expertise. Explain why keeping raw data on a device does not by itself make a learning system private.

Evidence, not credentials. We are describing work you can point at, in whatever form it exists.

The exercise

How we would look at it together

Evaluate a proposed federated training scheme for update leakage, malicious clients and withdrawal after participation.

← All 72 roles in the catalog