Aravind Sundaresan

Hi, I'm @aravindsundaresan,

Aravind Sundaresan

Distributed Systems & ML Infrastructure Engineer

Microsoft • Ex-Amazon

Building scalable inference infrastructure, GPU scheduling systems, and Kubernetes-native orchestration platforms.

LLM inference optimization
GPU cluster scheduling
Distributed systems
ML systems research

I'm an infrastructure engineer with 7+ years of end-to-end ownership — designing, launching, and maintaining large-scale distributed backends. At Microsoft and Amazon, I engineered platforms that thousands of engineers depend on without second thoughts: highly resilient active-passive metadata databases, adaptive Redis concurrency throttles, and automated hardware scheduler fleets designed to self-heal.

Since late 2023, my core direction has focused on ML systems and inference performance. I conduct active systems research to mitigate throughput bottlenecks in modern serving engines, shipping open-source scheduling fabrics (Clairvoyant, ACO, ServiceScope) designed for real-world production conditions with zero network or external API requirements.

[ SYSTEMS TOOLING DIRECTORY ]

// Systems Languages

Go C++ Rust Python C#

// Orchestration & Compute

Kubernetes Docker AWS Azure Terraform

// ML Serving Runtimes

vLLM ONNX Runtime PyTorch Ollama

// Distributed Data & Core

Redis Celery PostgreSQL Neo4j

Focused on inference infrastructure, GPU scheduling, distributed systems, and ML-native orchestration.

Open to ML systems, platform infrastructure, and distributed compute engineering roles globally. Based in Hyderabad and open to relocation.