Aishwarya 'Ash' Srivastava
cs @ asu
About me
I build infrastructure and tools for researchers and developers. I enjoy studying LLM alignment and optimized inference, especially how agents consider human feedback and behave efficiently. Current projects and experiments live at machinebrains studio.
Currently
- studying deceptive agent traces
- building faster inference systems
- teaching others about AI
Focus
- infra, full stack
- inference, alignment
- frontier labs, dev tools
Roadmap
product studio inc.
2026
engineering systems for agent memory, cognition, and personalization
arc lab
2026
working on latent space reasoning in llm architectures
louped
2026
opensourced harness i use for research
nexhacks
2026
first east coast winter and CMU visit; built an agentic scraper and shipped it on site
calhacks
2025
first SF hack; built an agentic workflow analytics tool and came home with a bigger fire