AI & Data Engineering Blog
Practical, technical articles on data platforms, AI systems and engineering leadership.
Call center speech analytics: measuring quality with speech recognition and LLMs
How to move from manually reviewing two percent of calls to scoring every call and chat against your own KPIs, using speech recognition, diarization and language models, with the safeguards that make the scores trustworthy.
· 5 min read
Self-hosting LLMs: sovereignty, quantization, serving and cost
When running language models on your own infrastructure makes sense, how quantization changes the hardware equation, which serving techniques matter, and how to estimate the real cost per token.
· 5 min read
Feature stores and ML pipelines for real-time trading analytics
How to compute features once and serve them consistently for training and live inference, with point-in-time correctness, streaming aggregation and the latency budgets trading use cases demand.
· 5 min read
AI agents in production: tool use, memory, guardrails and evaluation
What separates a reliable AI agent from an impressive demo: well-designed tools, deliberate memory, layered guardrails and an evaluation harness that tests behaviour, not just answers.
· 5 min read
Data engineering for brokers: designing a unified data warehouse with identity resolution
How to bring trading platforms, CRM, payments and back-office systems into one trustworthy model of the customer, and why identity resolution is the hardest and most valuable part.
· 5 min read
Building a production RAG pipeline: chunking, embeddings and retrieval evaluation
A practical guide to the parts of retrieval-augmented generation that decide quality in production: how you split documents, how you embed and index them, and how you prove retrieval actually works.
· 5 min read