Speaker

Rohan Mehta

Principal Data Scientist · Northwind AI

LLMOpsVector Search

Rohan builds large-scale LLM serving infrastructure at Northwind AI. His talks on cost-aware inference have become required viewing for teams shipping generative AI to production.

Talks

AI / ML

Serving Trillion-Token Models on a Budget

Practical patterns for batching, quantization, and autoscaling LLM inference without burning your cloud bill.

Austin

Jul 23, 2025 · 3:00 PM

Published papers

Self-Improving Training Pipelines with Active Data Selection

R. Mehta, V. Cruz

AI Systems · 2025 · 18 citations

Cost-Aware Scheduling for LLM Inference Clusters

R. Mehta, V. Cruz

AI Systems · 2025 · 19 citations

Retrieval-Augmented Generation Pipelines Over Proprietary Document Corpora

R. Mehta, X. Dubois

AI Systems · 2025 · 8 citations

Liquid Clustering for Adaptive Layout Optimization in Data Lakes

D. Chen, R. Mehta

Data Engineering · 2025 · 4 citations

Online/Offline Consistency in Real-Time Feature Stores

L. Zhao, V. Cruz, R. Mehta

ML Platforms · 2022 · 118 citations

Temporal Graph Models for Root-Cause Analysis in Microservice Architectures

R. Mehta, K. Nakamura

DevOps · 2021 · 82 citations

Cost-Based Optimization of Hybrid Cloud Query Execution

R. Mehta, I. Santos

Cloud · 2019 · 183 citations