# Ioana Mihăilescu

> Software Engineer @ Google DeepMind, Gemini Inference

Location: United Kingdom, United Kingdom
Profile: https://flows.cv/ioanamihilescu

I like to solve hard problems. Currently making Gemini faster and cheaper to run.

## Work Experience
### Software Engineer @ Google DeepMind
Jan 2024 – Present | London Area, United Kingdom
Improving the inference-time performance of the Gemini family models. 

- Optimised inference performance of Gemini 2-3 models across all model sizes. Contributed inference optimisations for the IMO gold model https://deepmind.google/blog/advanced-version-of-gemini-with-deep-think-officially-achieves-gold-medal-standard-at-the-international-mathematical-olympiad/
- Core contributor to long-context (1M tokens) infrastructure and distributed computing partitioning strategies.
- My contributions directly reduce latency and compute usage for models running in prod, on maaaany TPUs.

Areas of expertise – distributed systems, LLM scaling and partitioning strategies, TPU architectures, JAX.

### Personal Maths Tutor @ Imperial College London
Jan 2022 – Jan 2024
Teaching weekly Discrete Maths, Logic, and Algorithms tutorials to a group of 10 first-year students.

### Software Engineer Intern @ DeepMind
Jan 2023 – Jan 2023 | Greater London, England, United Kingdom

### Software Engineer Intern @ DeepMind
Jan 2022 – Jan 2022 | Greater London, England, United Kingdom

### Software Engineering Intern @ Arm
Jan 2021 – Jan 2021 | Cambridge, England, United Kingdom


## Education
### Masters of Engineering - MEng in Computing
Imperial College London


## Contact & Social
- LinkedIn: https://linkedin.com/in/ioanamih

---
Source: https://flows.cv/ioanamihilescu
JSON Resume: https://flows.cv/ioanamihilescu/resume.json
Last updated: 2026-04-05