pgvector in production: indexing, recall, and the queries that got slow
We built a semantic search and retrieval system for 12 million financial filings and real-time news articles. Our choice of vector database wasn’t a speci…
Read entryAlgorithmic Trading × AI Engineering
Engineering deep dives, from backtest to live trade.
Algorithmic trading × AI engineering — field notes from production.
Building a limit-order execution engine that respects the order book
Backtesting a high-frequency or market-making strategy using simple daily or even bar-by-bar data is a fast track to losing capital. In my early days buil…
Read entry
A nightly AI report that summarizes my bot’s trades and risk
I run a suite of systematic trading strategies across several crypto perpetual exchanges and equity brokers. Every night around 11:00 PM, I used to find m…
Read entry
Jenkins vs GitHub Actions for ML-service CI: what I kept and what I dropped
Two years ago, my team was responsible for maintaining the production deployment pipelines of a suite of real-time machine learning models. These models p…
Read entry
Batching strategy for LLM inference: throughput vs tail latency
During high-volatility market events, such as an unscheduled Federal Reserve rate announcement, my team's algorithmic trading infrastructure processes a m…
Read entry
LangGraph state machines: modeling a multi-step agent as a graph, not a prompt chain
A few months ago, I was tasked with building an automated quantitative research agent. The goal was straightforward: ingest a ticker symbol, pull real-tim…
Read entry
Detecting regime change with a two-state hidden Markov model
My trend-following systems spent the summer of 2023 getting shredded. I was running a systematic breakout strategy on liquid futures, and the market enter…
Read entry
Position sizing with the Kelly criterion: where it broke in live trading
If you spend enough time in the quantitative finance literature, you will inevitably run into the Kelly criterion. It is presented as the holy grail of po…
Read entry
Speculative decoding on vLLM: the latency win and the gotchas
We run a real-time sentiment and market-impact parsing engine that processes news feeds, regulatory filings, and earnings transcripts. Our SLA requires us…
Read entry
Cross-sectional momentum vs mean reversion: a practitioner’s comparison
Two years ago, my team was tasked with scaling a mid-frequency long-short equity book from $15M to $80M. Up to that point, we had run simple time-series m…
Read entry