Skip to content
← Sanas

Member of Technical Staff, ML Inference Engineering

Sanas · Bengaluru, India

Applied AIonsitestaff
Apply on the lab’s site ↗

At a glance

Highlights

  • Bring real-time speech and language models on-premise at massive scale.
  • Shape core inference infrastructure inside sovereign data centers.
  • Push compute limits for private, reliable low-latency serving.

Ideal candidate

Deeply hands-on systems builder who shapes architecture and elevates teammates. Thrives on hard latency challenges and wants ownership driving real-time speech AI in demanding on-prem environments.

Requirements

  • 8+ years writing high-quality, high-performance code, including 5+ years focused on ML systems
  • Experience with C/C++/Rust and Python
  • Deep familiarity with modern NVIDIA GPU architectures, CUDA, and low-level system profiling
  • Hands-on experience with ML compilers and optimization frameworks like TVM, TorchInductor, TensorRT, Triton
  • Experience building or extending model serving infrastructure including custom C++ backends for Triton
  • Fluency across AI serving stack from kernels and quantization to schedulers, state management and autoscaling
  • Record of shipping research or systems that others build on

Lab profile

About Sanas

Real-time speech AI platform for accent translation, noise cancellation, and clearer communication.

What they build

  • Real-time speech AI platform
  • Accent translation
  • Noise cancellation

Known for

  • Real-time speech processing
  • ML inference engineering
  • LLM post-training
  • Developer platform and SDKs
More about Sanas →
Apply on the lab’s site ↗

First seen · Last seen