Research Engineer
Atul Saxena
I build the environments models are trained in, and the tools that show what they learned.
- RL Systems
- Interpretability
- ML Infrastructure
Research Engineer
Atul Saxena
I build the environments models are trained in, and the tools that show what they learned.
Will this model fit, and how fast will it run?
A hardware-aware LLM/VLM feasibility estimator: parameter and quantization memory modelling, KV-cache and context scaling, and inference latency/throughput prediction across CPU and GPU backends.
Working out whether a given model will actually run on given hardware — and at what speed — normally means downloading it and finding out.
status: Active