Facebook pixel

Software Engineer
Inference
Posted on 2/14/2022
INACTIVE
Locations
Menlo Park, CA, USA
Experience Level
Entry
Junior
Mid
Senior
Expert
Desired Skills
CUDA
C/C++/C#
Pytorch
Tensorflow
Go
Requirements
  • You have experience with serving ML models
  • You are proficient in C++ and/or Golang
  • You have experience designing, implementing, and maintaining a production service at scale
  • You have experience in performance benchmarking, profiling, and optimization
  • You have experience working with accelerators (GPUs and/or TPUs)
  • You are familiar with autoregressive sequence models, such as Transformers
  • You have experience in building and scaling large API services
  • You have experience with programming with frameworks like CUDA, JAX, Pytorch or Tensorflow
  • This is NOT a hard list of requirements - we welcome candidates with a combination of these skills and are really excited about those willing to learn!
Responsibilities
  • Develop and manage a state-of-the-art system for serving large natural language models with low latency and high availability
  • Collaborate closely with experienced Software and Machine Learning Engineers
  • Be part of a fast-growing team in a well-funded startup
  • Scale and improve the resiliency of Cohere's API
Cohere

11-50 employees

Natural language processing software
Company Overview
Cohere's mission is to build machines that understand the world, and to make them safely accessible to all.