acompa blog

DSPy is a useful AI workflow development tool, but its runtime configuration introduced issues for our production workflows.

How the emergence of useful agentic coding in late 2025 might affect everything.

Lessons from 39 job conversations after a layoff from Spotify, and what the market looks like for ML engineers in 2024.

How Airbnb scaled its data infrastructure with Airflow, Zipline, and other frameworks for ML at hundreds-of-models scale.

Trends from RecSys 2018: contextual bandits, deep learning for recommendations, and fairness in personalization.

Speaking at SciPy 2017 about modeling trends in music, plus highlights from other talks at the conference.

Teaching git fundamentals to iHeartRadio's algorithms team to scale collaboration beyond single-owner folders.

A primer on L1, L2, and ElasticNet regularization and why they help models generalize.

Detecting unusual spikes in Twitter community activity using time series decomposition, built at Betaworks with Rohit Jain.

Presenting an autoscaling project at Surge 2012 and learning that good instrumentation matters more than a good forecasting model.

A step-by-step guide to installing R and rpy2 on a bare EC2 instance for Python developers who need R's statistical packages.

How sleep deprivation during a busy summer led to silly bugs in a toy virtual memory manager.

Why traditional grading ignores question difficulty, and how item response theory offers a better measure of student ability.