Serving LangChain agents in production with LangServe
Eight months ago, our algorithmic trading desk transitioned its market sentiment and macro news analysis pipeline from standalone Python scripts to an aut…
Read entryAlgorithmic Trading × AI Engineering
Engineering deep dives, from backtest to live trade.
Algorithmic trading × AI engineering — field notes from production.
OpenTelemetry tracing across Spring services: from zero to useful in a week
Three months ago, our high-frequency order-routing architecture started dropping trades during peak volatility. We run a Spring Boot microservices mesh ha…
Read entry
Why I chose Gemma 4 E4B over 26B for structured JSON output
In our automated algorithmic trading pipeline, prompt engineering is a liability. Every market tick requires us to parse un-structured news feeds, SEC fil…
Read entry
Giving a research agent memory with Redis and pgvector
When I deployed my market research agent to track earnings calls and regulatory filings, it hit a wall within two weeks. The LLM had a context window of 1…
Read entry
Serving embeddings at scale with ONNX Runtime
Last quarter, my team took over the real-time feature generation pipeline for our order-book anomaly detection models. The core of the pipeline relies on…
Read entry
Grammar-constrained decoding for reliable structured output
Two months ago, my production algorithmic trading system started dropping order executions during volatile market conditions. The issue wasn't network lat…
Read entry
Vector search over filings: building a quant analyst’s memory
I spent three weeks watching an event-driven backtest fail for a reason that had nothing to do with my signal math.
Read entry
Multi-environment GitOps: one repo layout that survived dev, staging, and prod
Two years ago, I broke production during a high-volatility trading session because our GitOps repository structure lied to us.
Read entry
Discretionary entry + systematic exit: how I handle leverage
I used to blow up accounts on leveraged crypto futures and index options for a very specific reason: I let my discretion stay in the trade for too long.
Read entry
HPA in practice: why CPU-based autoscaling kept scaling at the wrong times
Three months ago, our crypto market data ingestion pipeline hit a wall. During high-volatility events, execution latency spiked from 15ms to over 800ms. O…
Read entry