All open roles
Engineering
Machine Learning Engineer, Inference
San Francisco
Full-time
Make our models start speaking faster and cost less to serve, on every kind of hardware.
About the role
Inference is where research meets real calls. You will own the systems that serve our models with low latency at global scale.
What you will do
Optimize model serving across GPUs and edge devices
Build tools to profile and test latency
Partner with research on model design for fast inference
What you will bring
Experience serving large models in production
Comfort with CUDA, C++ or Rust
A habit of measuring before optimizing
Apply for this role
We review every application and reply within two weeks.
Get started today
Talk to an expert.
Meet someone from our team and see how Halvora can power voice experiences your callers will remember.
Start building.
Spin up a voice agent or call our models from the API, and go live the same day.
We’re hiring!
Help build voice that feels human