Progressive delivery of a model service with ArgoCD: canary and instant rollback
A silent failure mode in production machine learning is rarely a clean crash. It is usually a subtle drift in the feature pipeline, an unhandled NaN in a…
Read entryAI Engineering
A free contact address with Cloudflare Email Routing — no mail server
Automated trading infrastructure demands extreme reliability, minimal operational surface area, and zero unnecessary overhead. When building out-of-band c…
Read entry
Debugging intermittent Chrome connection failures: HTTP/3 QUIC on LiteSpeed
In our algorithmic trading setup, milliseconds are the baseline currency. We run a hybrid AI engine that streams sub-second inference updates—predicting v…
Read entry
Point-in-time Postgres recovery on Kubernetes: CloudNativePG backups to object storage
It was 14:18 UTC on a Thursday when our main Slack alert channel lit up. A rogue autonomous agent run, deployment code-named "Project Oracle", had entered…
Read entry
Redis as an agent’s working memory and rate limiter
Building autonomous, multi-agent execution systems for quantitative trading workflows sounds great until you put them into production.
Read entry
Excluding your own traffic from GA4 with an internal-traffic filter
When you build and manage high-traffic analytics systems, your worst enemy isn't raw volume—it is dirty data.
Read entry
Running multimodal inference on consumer GPUs: what actually fits
I recently built an automated monitoring agent to parse order-book heatmaps, trading execution logs, and live liquidity charts. The goal was simple: run a…
Read entry
Durable agents: pairing LangGraph with Temporal so a crashed run resumes
Building complex LLM agents with LangGraph is incredibly intuitive until you run them in production on workloads that take minutes or hours to complete.
Read entry
Quantizing a 70B model to fit 2x RTX 3090: AWQ vs GPTQ in practice
Deploying a 70-billion parameter model like Meta-Llama-3-70B on a local workstation is the holy grail for trading desks and quantitative shops looking to…
Read entry
KV cache sizing for multi-GPU vLLM deployments
We run high-frequency, event-driven sentiment analysis pipelines that parse corporate earnings transcripts, SEC filings, and real-time news feeds. Our pip…
Read entry