-
I Grilled Another Agent Candidate: 46-Minute Mock Interview
A 46-minute 1v1 Agent engineer mock interview: deep-diving two personal projects, plus RAG, Agent evaluation, Skills, MCP, prefix caching, and Q&A.
·agent面试llmai模拟面试求职rag -
Interviews Aren't Exams, They're Mutual Selection
After 100+ Agent interviews, how I redefined it: apply early, calibrate constantly, review recordings, ask hard questions, and meet founders as equals.
·agent面试求职职业发展ai -
For Everyone Who Wants Into Agents But Doesn't Know Where
Joye's Agent Engineer Onboarding Guide v1.0: what an Agent is, why now, how to start, and how to land a job — for anyone who wants in but doesn't know where.
·agentllm入门学习路线求职ai -
A 1h19m Agent Engineer Mock Interview: What We Asked
An 80-minute mock interview with a dev pivoting to Agent work. Every question, his answers, our feedback, and how I would answer them better.
·agent面试llmai模拟面试求职 -
Reading OpenHarness: Inside an 11,733-Line Agent Harness
HKUDS open-sourced OpenHarness, an Agent Harness matching Claude Code. My notes from a day reading its core architecture: Phase 1, CLI startup to Agent Loop.
·ai agentharnessclaude codeopenharness源码解析python -
A Sophomore Intern's Field Guide to Agent Dev Interviews
After interviewing nearly 10 AI startups, what Agent-role interviews actually test, and the things that matter a hundred times more than memorizing answers.
·实习agentllm面试ai -
FeedForward and the Transformer Block: The Other Half
A deep dive into the FeedForward network and how RMSNorm, RoPE, Attention, and FeedForward assemble into a complete Transformer Block.
·llmtransformerminimindfeedforwardswigluarchitecture -
Understanding Attention: From Q, K, V to Multi-Head
A deep dive into Attention, the Transformer's core engine: grasp Q, K, V via a database-query analogy, master Multi-Head, and clear up Softmax vs RMSNorm.
·llmtransformerminimindattentionmulti-head
Blog
Page 1 - Showing 8 of 12 posts