Principal Software Engineer, Machine Learning Infrastructure

Snap Snap · Consumer · Palo Alto, CA +5

Principal Software Engineer focused on ML Inference Platform services, designing, implementing, and scaling critical engineering components for ML inference and deployment. The role involves technical strategy, architecture, and advocating for best practices in availability, scalability, operational excellence, and cost management, with a focus on large-scale distributed systems and high-throughput RPC services.

What you'd actually do

  1. Oversee technical strategy and architecture in ML Inference Platform services
  2. Design, implement, and scale critical engineering components and services to support ML inference and deployment
  3. Work across teams to understand product requirements, evaluate trade-offs, and deliver the solutions needed to build innovative products or services
  4. Advocate for and apply best practices when it comes to availability, scalability, operational excellence, and cost management
  5. Provide technical direction that influences the entire company

Skills

Required

  • excellent programming and software design skills
  • debugging
  • performance analysis
  • test design
  • operating highly-available systems at scale
  • proactively learn new concepts and technology and apply them at work
  • solving ambiguous problems
  • collaboration and mentorship skills
  • technical leadership or acting as the domain-expert to a technical organization
  • technical leadership/ownership and setting technical direction for engineering projects
  • architecting, designing, and developing large scale distributed systems and high-throughput RPC services

Nice to have

  • Tensorflow
  • PyTorch
  • Kubernetes
  • GPU
  • LLM inference

What the JD emphasized

  • technical leadership
  • technical direction
  • architecting, designing, and developing large scale distributed systems and high-throughput RPC services

Other signals

  • ML Inference Platform services
  • ML inference and deployment
  • large scale distributed systems
  • high-throughput RPC services