Staff Data Science Engineer Distributed ML & Streaming

High-throughput data engines & production ML.

Building sub-millisecond streaming feature stores, distributed lakehouse pipelines, and calibrated predictive models running in high-stakes production.

PyTorch · Spark · Kafka · Ray <12ms p99 Latency 1.8B+ Events/Day
Portrait of Ashley Miller, Data Science Engineer
Production: 99.98% SLA
Ashley Data Science Engineer
Ashley Miller, Data Science Engineer
10+ Years ML & Data
Engineering
Ashley Remote / Distributed

Data Engineering & Applied Science

Rigorous modeling meets real-world distributed scale.

Bridging the gap between mathematical inference and high-throughput production infrastructure. A machine learning model is only as dependable as the pipelines that feed it and the latency bounds it upholds.

My focus is end-to-end: formulate statistical loss surfaces, eliminate training-serving skew with declarative feature stores, and deploy quantized models into low-latency serving clusters with automated drift telemetry.

More about me

Statistical Rigor

Principled hypothesis testing, probability calibration, and continuous drift detection to ensure models remain dependable in production.

Low-Latency Streaming

High-throughput pipelines with Spark, Kafka, and Redis delivering sub-millisecond features to real-time inference endpoints.

Reproducible MLOps

Hermetic Docker environments, strict schema contracts with dbt, and automated continuous evaluation with Ray and Triton.

Technical Capabilities

Data systems & production ML, from architecture to SLA.

Explore services

Production ML & Predictive Systems

High-throughput, calibrated machine learning models designed for real-time inference.

Explore service

Distributed Data Engines & Streaming

Real-time event streaming and scalable Lakehouse data platforms.

Explore service

MLOps Infrastructure & Model Serving

Robust model registries, serving clusters, and automated continuous evaluation.

Explore service

Working principle

“In high-stakes production, an accurate model that misses SLA latency bounds is indistinguishable from a total system failure.”
Ashley Miller, Data Science Engineer Read the journal