← Back to Directory

American Express

Large Enterprises

Screna has 10 American Express interview write-ups. The most reported round is the system design round (5).

10 interview notes · updated Jun 2026

American Express·AI Engineer·Onsite - System Design / Architecture

Jun 2026
30-minute system design round at Amex for an AI Engineer role. The whole thing was a single RAG design case, which sounds focused until you realize how many layers they actually want you to cover in half an hour.
  • Design a Retrieval-Augmented Generation (RAG) system over a corporate document corpus. Walk through ingestion, retrieval, generation, evaluation, and operational concerns.

“They gave 30 minutes for this and I spent way too long on chunking strategy upfront.”

View Post

American Express·AI Engineer·Onsite - System Design / Architecture

Jun 2026
System design round at Amex for an AI Engineer role, focused almost entirely on memory architecture for AI agents. It went deeper than I expected and I definitely undersold a few areas.
  • How would you design the memory system for an AI agent, covering both short-term working memory and durable long-term storage?
  • What's the distinction between episodic and semantic memory in an agent context, and how does that affect your storage design?
  • Walk me through the retrieval strategies you'd consider for an agent's long-term memory. When would you use a vector store versus a structured database versus hierarchical summaries?
  • How would you handle forgetting or compaction in an agent's memory? What policies would you apply and why?
  • How would you design the read and write APIs for an agent's memory layer?
  • How do you maintain consistency in shared memory when multiple agents or concurrent sessions are reading and writing at the same time?
  • How would you evaluate whether your agent's memory system is actually working well in production?

“I started with context windows as working memory and then talked about external stores for persistence.”

View Post

American Express·AI Engineer·Onsite - System Design / Architecture

Jun 2026
System design round at Amex for an AI Engineer role, focused almost entirely on fault tolerance and reliability for AI systems. Pretty deep technically, more distributed systems than ML, which I wasn't fully expecting.
  • How would you design a fault-tolerant AI system that can recover from failures? Walk through your approach to stateless versus stateful components and how you'd handle persistent state.
  • How do you ensure idempotent request handling when retrying LLM or tool calls, and when do you actually need exactly-once semantics?
  • What's your strategy for retry logic and circuit breakers specifically around LLM API calls and external tool integrations?
  • How would you design graceful degradation when a downstream model or retrieval backend becomes unhealthy?
  • How do you approach multi-region replication and failover for AI systems, including both model artifacts and runtime state?
  • How do you handle prompt and tool versioning to maintain reproducibility across different model versions in a production system?

“This was the main question and it sprawled for like 40 minutes.”

View Post

American Express·AI Engineer·Onsite - System Design / Architecture

Jun 2026
System design round at Amex for an AI Engineer role, focused entirely on long-running multi-agent systems. Pretty deep cut for a single question session. Left feeling like I'd covered maybe 60% of what they were actually looking for.
  • How would you design and operate a multi-agent system that runs for hours or days, potentially with agents cooperating with each other? Walk through how you'd handle durable state, crash recovery, idempotency, retries, supervision, inter-agent communication, observability, cost management, and human-in-the-loop interrupts. Also cover failure modes like drift, looping, and runaway costs.

“This is basically a full distributed systems design question dressed up in AI clothing, and I didn't fully register that until I was halfway through rambling about checkpointing.”

View Post

American Express·AI Engineer·Onsite - System Design / Architecture

Jun 2026
System design round at Amex for an AI Engineer role, pretty deep on the infrastructure side of multi-agent systems. The whole session was basically one big question broken into layers, and they kept pushing further than I expected.
  • How would you design a multi-user AI agent system that keeps each user's context fully isolated while sharing underlying infrastructure like model servers, KV-cache pools, and vector stores?
  • Walk me through how you'd implement fair queueing and rate limiting across concurrent users hitting shared model inference endpoints.
  • How do you balance request batching for inference throughput against per-user latency SLAs when load is uneven?
  • If multiple concurrent sessions can update shared agent state, what consistency guarantees would you provide and how would you implement them?
  • How would you instrument a multi-user agent system for observability, specifically per-user distributed tracing across tool calls and model invocations?
  • How would you test concurrency correctness in an AI agent system, particularly for race conditions in shared state and session isolation?

“This is where I spent most of my time and still felt like I left things on the table.”

View Post

American Express·AI Engineer·Technical Phone Screen

May 2026
Technical screen for an AI Engineer role at Amex, pretty much one big conceptual question about how LLMs, RAG, and agents relate to each other. Felt like a solid conversation but also the kind of question where you can ramble forever and not actually say anything useful.
  • Walk through the differences between a base LLM, a RAG system, and an autonomous agent. How do they relate to each other, when would you use each, and how do they compose?

“This question looks clean on paper but it's actually easy to fumble because the three concepts bleed into each other and you can lose the thread fast.”

View Post

American Express·AI Engineer·Technical Phone Screen

May 2026
Technical interview at American Express for an AI Engineer role, focused almost entirely on how you evaluate LLM and agent systems end-to-end. Pretty deep dive, not the usual ML fundamentals stuff.
  • How would you design an end-to-end evaluation framework for an LLM or AI agent system, covering both offline and online metrics?
  • When using an LLM as a judge to score outputs, how do you make sure the judge itself is calibrated and trustworthy?
  • What metrics do you track specifically for agent systems, like tool use and plan execution?
  • How do you handle regression testing when you swap out or upgrade the underlying model?
  • How do you balance automated evaluations with human evaluation, and when do you trust one over the other?
  • What are the main pitfalls in LLM evaluation, like eval set contamination or distribution drift?

“This was the core question and it sprawled in a bunch of directions.”

View Post

American Express·AI Engineer·Technical Phone Screen

Apr 2026
A 20-minute Karat-style debugging round for an AI Engineer role at American Express. The whole thing was about reading test output fast and pinpointing bugs, not writing a ton of code from scratch. Two parts: find and fix a broken function, then write a new one to make extra tests pass.
  • You're given a set of Python classes and a failing test suite. Read the test output, identify which function contains the bug, explain why the tests are failing, and fix the function with a minimal change.
  • Based on a short spec, write a new function so that a set of additional tests passes.

“The pressure here isn't writing code, it's reading test failure messages and being precise about what's actually broken.”

View Post

American Express·AI Engineer·Technical Phone Screen

Apr 2026
Went through a technical screen for an AI Engineer role at American Express that was almost entirely focused on LLM security. Not what I expected from a fintech company but in hindsight it makes sense given how much they're investing in agentic systems. The depth they wanted was real.
  • What is the difference between direct prompt injection and indirect prompt injection, and why does the distinction matter for agent systems?
  • Walk through the main threat models you'd consider when deploying an LLM-based agent: data exfiltration, privilege escalation, jailbreaks, and tool misuse.
  • What mitigation strategies would you use to defend against prompt injection, and what are the concrete limits of each?
  • How would you design an end-to-end defense strategy for an LLM agent that has access to external tools and retrieval systems?

“I had a decent answer here.”

View Post

American Express·AI Engineer·Technical Phone Screen

Mar 2026
Technical interview at American Express for an AI Engineer role, focused almost entirely on how agents extend LLM capabilities through tooling. Pretty deep session, they clearly wanted someone who'd actually built this stuff rather than just read about it.
  • How does tool use and function calling work in AI agents? Walk through schema design, how the agent routes to the right tool, and how errors get handled.
  • How would you design a plug-in or MCP-style integration layer for an agent system?
  • When does it make sense to give an agent the ability to write and execute code as a tool?
  • How does retrieval fit into the capability stack of an agent, and how is it different from just using a bigger context window?
  • Explain the planner/executor pattern in agentic systems and when you'd use it.
  • How does an agent discover and select which tools to use at runtime, especially when the tool set is large?
  • How do you decide whether a new capability should be added as an external tool versus baked into the model through fine-tuning or training?

“I started with schema design and talked about strongly typed inputs, required vs optional fields, and keeping descriptions tight so the model doesn't hallucinate parameters.”

View Post