Aayush Garg
Aayush Garg
Forward deployed ML engineer at Applied Computing
I build and deploy AI systems, from first principles to production.
Right now that means forecasting, anomaly detection and optimisation for energy operations at Applied Computing. Before that, I shipped image generation and enhancement pipelines at Jiffy and Flixstock. Outside work, I rebuild language models from scratch and write about what I learn.
Now October 2026
Working on
Forecasting and anomaly detection for refinery operations
Applied Computing
Building
FlashAttention2 from first principles
building-from-scratch
Live
Updated every 15 minutes
Latest post
Kalman Filters and Smoothing for Time-Series Data
15 Jul 2026 · 16 min
Path
-
2015 to 2022
Research
PhD at TU Delft, then research geophysicist at Shell, applying deep learning to imaging and inversion problems.
-
2022 to 2026
ML development
Diffusion pipelines at Flixstock. The image enhancement pipeline and Smart Redraw at Jiffy.
-
2026 onward Now
Applied ML in the field
Production AI for refineries and energy operations at Applied Computing.
Writing All writing
- Time Series 16 min
- Tools & Infra 9 min
- Local LLMs 16 min
- Local LLMs 6 min
- Local LLMs 11 min
Built All work
-
building-from-scratch
Language models from first principles: GPT-2, a BPE tokenizer with a Rust encoder, KV cache, SFT and GRPO.
-
India Weather
Weather and air quality across Indian cities on one map, with 24-hour history.
-
Browser tools
Image, JSON, YAML, LaTeX and diff utilities that run entirely in your browser.