hi, i'm nikitha

I lead inference at Together.ai in San Francisco.

My career has taken me through studying electrical engineering, verifying chips, building virtualization for data centers, deploying Kubernetes in large enterprises, and scheduling jobs across CPUs, GPUs, and TPUs. I've also worked on creating app-level abstractions for distributed systems.

I invest in cloud, compute, infra for AI/ML, dev tools, and data.

featured writing

Inference beyond the tokens

Insights on making AI inference faster, cheaper, and better.

What goes into an inference stack?

A deep dive into the components of an inference stack

On AI, fig trees, and choosing the next branch

The AI siren song is calling

view all posts →

select investments

All-in-one platform to host, manage, and monitor headless browsers in the cloud.

Generative media platform for developers. Build the next generation of creativity with fal. Lightning fast inference.

Machine identity for the AI era. Empowering AI & humans with dynamic, contextual access across networks.

view all investments →