Mira Castellan
Senior Machine Learning Engineer
Brooklyn, New York | mira@example.com
Portfolio: jobswithpay.com/p/sample | Website: example.com | LinkedIn: example.com/linkedin | GitHub: example.com/code | Google Scholar: example.com/scholar | ORCID: orcid.org/0000-0002-1825-0097
Summary
I build the systems that serve large language models: fast inference servers, careful evaluation and the tools around them. For six years I have worked between research and production. I like small, clear code and measurements that people can trust.
Experience
Senior Machine Learning Engineer
Mar 2023 to Present
Tidewater AI, New York
- Lead the inference team of four engineers for the company's chat product.
- Cut the median response latency by 38% with speculative decoding and a new batch scheduler.
- Built the evaluation harness that the research team uses for every model release.
Machine Learning Engineer
Jun 2020 to Feb 2023
Kestrel Robotics, Boston
- Trained the vision models for warehouse robots, from data pipeline to deployment on the robot.
- Moved model training to a shared GPU cluster and cut the cost for each experiment by half.
Data Scientist
Aug 2018 to May 2020
Orchard Health, Boston
- Built the risk models for the care team, used for 40,000 patients each month.
Projects
tinyserve
A small inference server for language models, written in Rust. It runs one model on one GPU with continuous batching.
Technology: Rust, CUDA, gRPC
evalcards
Short, repeatable evaluation reports for model releases, as static web pages.
Technology: Python, DuckDB
Batch scheduler notes
A written guide to batch scheduling for model serving, with measurements on three GPU types.
Technology: Writing
Skills
- Python: torchwave/torchwave, 14 merged pull requests
- Rust: ferrox/ferrox-runtime, 5 merged pull requests
- PyTorch: torchwave/torchwave, 14 merged pull requests
- CUDA: servekit/servekit, 9 merged pull requests
- AI agents: agentkit/agentkit, 9 merged pull requests
- vLLM: servekit/servekit, 9 merged pull requests
- Triton: triton-kernels, 24 stars
- Model evaluation: evalcards, 41.3K downloads a month
- Computer vision: mira-sample/grasp-det-small, 1,900 downloads a month
- SQL: duckling-db/duckling, 3 merged pull requests
Kubernetes, Distributed training
The text after a skill is public work that JobsWithPay checked. See jobswithpay.com/p/sample.
Research
7 papers, 402 citations, h-index 5.
- Speculative Batching: Lower Latency for Shared Inference Servers. MLSys, 2024, 214 citations.
- When Do Evaluation Sets Go Stale? A Study of 40 Model Releases. NeurIPS Datasets and Benchmarks, 2025, 88 citations.
- Grasp Detection with Few Labels in Warehouse Scenes. ICRA, 2022, 61 citations.
- Calibrated Risk Scores for Care Management. Machine Learning for Health, 2020, 23 citations.
- Draft Models That Know When to Stop. arXiv, 2026, 3 citations.
Education
University of Michigan
2016 to 2018
MS, Computer Science
University of Lisbon
2012 to 2016
BS, Mathematics