Plaid Machine Learning Engineer interview questions

3 Machine Learning Engineers have shared notes from their Plaid interviews, with the questions they were asked in each round. That is 14% of the 21 Plaid interview notes on Screna AI.

3 Machine Learning Engineer interview notes

Plaid·Machine Learning Engineer·Onsite - System Design / Architecture

Jun 2026
System design round at Plaid for an MLE role, focused entirely on building a fraud detection system for a fintech data-connectivity platform. The question was massive and kept branching into follow-ups I wasn't fully ready for. Left feeling like I covered maybe 70% of what they wanted.
  • Design an end-to-end ML system for detecting fraud across the full user lifecycle on a fintech data-connectivity platform, covering bank-account linking, identity verification, and suspicious transaction behavior. The system needs near-real-time scoring and graded actions (allow, step-up, review, block) with a low false-positive rate.
  • A fraud ring is sharing a single device across 50 newly created accounts, each linking a different bank. How would your graph features and velocity counters detect this, and how fast?
  • Your offline PR-AUC improved after a model update but online fraud loss didn't drop. What are the likely causes and how would you diagnose it?
  • How do you evaluate and set thresholds for a model when its own blocks are suppressing the labels you'd use to measure it? What strategy keeps your measurement unbiased?
  • The model is flagging a legitimate immigrant population at a higher rate due to IP and geolocation features. How do you detect this disparate impact and fix it without gutting recall?

“This is the main question and it's enormous.”

View Post

Plaid·Machine Learning Engineer·Onsite - System Design / Architecture

May 2026
Plaid ML engineer interview focused entirely on designing an evaluation and debugging framework for a production RAG semantic search system in fintech. Five-part deep dive, very systems-thinking heavy, less about coding and more about whether you can reason about quality measurement end to end.
  • You own a production RAG-based semantic search feature for a fintech product. Design a lightweight but production-ready evaluation and debugging framework covering retrieval quality, answer quality, faithfulness, latency, and cost as offline metrics. What do you measure at each stage and what thresholds would you hold?
  • What online signals would you track for this system, and how would you run a controlled experiment for a retriever or prompt change without contaminating results?
  • Where does your benchmark data come from, how do you create labels, and how do you keep the eval dataset fresh without breaking historical comparisons?
  • How do you integrate evaluation into CI/CD, what are your model-release gates, and what would you alert on in production dashboards?
  • Search relevance suddenly drops in production. Walk through exactly how you'd localize the failure to a specific pipeline stage, confirm the root cause, apply a fix, and prove the fix actually worked.
  • Your LLM-as-judge for faithfulness is itself a model. How do you evaluate and trust the judge, and what do you do when the judge disagrees with human labels?
  • A new retriever improves your offline ranking metric but loses the online A/B test on answer-acceptance. How do you reconcile that, and which signal do you believe?
  • A regulator asks you to prove that a specific user could not have retrieved a document they weren't entitled to. What in your logging and eval system lets you answer that, and how do you proactively test for permission leaks?
  • The corpus churns 10% daily but is 90% stable week over week. How do you keep retrieval quality stable across re-indexing, and how would you detect a silent indexing failure on the churning slice?

“This was the core of the whole interview and I spent probably too long on the retrieval side before getting to faithfulness.”

View Post

Plaid·Machine Learning Engineer·Technical Phone Screen

May 2026
Interviewed for an MLE role at Plaid and got a data structure question that looked deceptively simple on the surface. Two mappings, one lookup function, and a bunch of edge cases to reason through.
  • You have two mappings: one from bank codes to canonical institution IDs, and another from institution IDs to one or more bank records. Preprocess these mappings and implement a lookup function that, given a bank code, returns all associated banks. Walk through your data structure choices, time complexities, and how you handle missing codes or duplicate entries.

“My first instinct was to just chain the two lookups at query time and call it done.”

View Post