Principal ML Inference Engineer: Scale, Strategy & Impact

Snap; New York (NY); On-site; USD 276,000 - 414,000; Full time

Benefits offered by this job

Equity in RSUs

Job summary

Snap Inc. is seeking a Principal Software Engineer for the ML Inference team in NYC. This role leads technical strategy, architects high‑scale inference services, and drives scalable deployments across product lines.

You will collaborate with multiple teams to translate complex requirements into robust systems, promote reliability and cost efficiency, and mentor engineers while shaping the company’s ML platform direction.

Qualifications

• Bachelor's degree or higher in a technical field with substantial software development experience.
• 10+ years in software development; leadership or domain expert experience is required.
• Experience architecting large scale distributed systems and RPC services.

Responsibilities

• Oversee technical strategy and architecture in ML Inference Platform services.
• Design, implement, and scale core components for ML inference and deployment.
• Collaborate across teams to translate requirements into scalable solutions.
• Advise on availability, scalability, and cost management.
• Provide technical direction influencing the company.

Skills

Software design

Debugging

Performance analysis

High availability

Mentorship

Collaboration

Education

Bachelor's in CS

Master's/PhD (optional)

Tools

TensorFlow

PyTorch

Kubernetes

GPU

LLM inference

Job description

Snap Inc. is seeking a Principal Software Engineer for the ML Inference team in NYC. This role leads technical strategy, architects high‑scale inference services, and drives scalable deployments across product lines.

You will collaborate with multiple teams to translate complex requirements into robust systems, promote reliability and cost efficiency, and mentor engineers while shaping the company’s ML platform direction.