Field notes · 31 AI engineering articles
AI Engineering Articles
From the review desk
Production AI systems: inference and serving, retrieval, agents, evaluation and AI security, multimodal and edge pipelines, and AI-native product architecture.
From Forward Days to the Jury Room: My Swiss {ai} Weeks Journey in Zürich 🇨🇭
A week of AI, hackathons, people, conversations, mentoring, volunteering and a lot of unexpected memories.
All articles
-
Transformer Inference, From HTTP Request to the Next Token
A systems-level tour of prefill, decode, batching, memory movement, and the scheduling decisions that determine real-world LLM latency.
-
KV Cache Engineering for LLM Inference
How to size, allocate, reuse, compress, and evict the state that makes autoregressive decoding practical.
-
Semantic Caching Without Serving the Wrong Answer Faster
A production design for similarity keys, freshness, authorization, invalidation, and the economics that determine when semantic reuse is safe.
-
Speculative Decoding Without Hand-Waving
Draft models, acceptance math, tree proposals, and the operational details that decide whether speculation makes serving faster.
-
Synthetic Evaluation Data That Finds Real Failures
How to generate, filter, diversify, and maintain synthetic cases without turning an evaluation suite into a mirror of its generator.
-
The LLM Gateway Is a Policy Engine, Not a Proxy
Designing the routing, budgets, identity, resilience, and evidence layer between products and a changing model portfolio.
-
Privacy-Preserving AI Is a Dataflow Architecture
Purpose limitation, minimization, isolation, retention, redaction, and verifiable deletion across retrieval, models, tools, traces, and feedback loops.
-
Incident Response for Systems That Can Be Wrong Fluently
A response playbook for quality regressions, prompt attacks, retrieval contamination, runaway agents, cost spikes, and provider failures.
-
Production RAG Is an Evidence Pipeline, Not a Vector Search
Designing retrieval-augmented generation around ingestion quality, query planning, evidence assembly, and verifiable answers.
-
Hybrid Lexical and Vector Search
A practical design for candidate generation, score normalization, rank fusion, metadata filters, and retrieval evaluation.
-
Rerankers: The Quality Layer Between Search and Generation
How cross-encoders, late interaction, listwise ranking, and calibration turn noisy candidates into usable evidence.
-
Engineering the Agent Tool Loop
A concrete architecture for tool selection, state transitions, permissions, budgets, and recovery in production agents.
