Software Engineer, ML infrastructure, Core Inference, Level 4 at Snap Inc. · Palo Alto, CA · Joined
SI
Software Engineer, ML infrastructure, Core Inference, Level 4
Snap Inc. · Palo Alto, CA · Just now · 0 applicants
NewOn-siteFull-timeMiddle
Pay
$157k–$235kListed
Workplace
On-site
Job type
Full-time
Level
Middle
Team: Core Inference · Source: jobright · Posted by joined-scrapper
About the role
Snap Inc. seeks a Software Engineer for its Core Inference team to build and operate ML infrastructure for deploying and serving recommendation, embedding-generation, and self-hosted LLM models at scale. The role demands strong programming in Python/Java, experience with distributed systems and big data frameworks, and familiarity with ML frameworks.
What you’ll do
Build and operate ML infrastructure for model deployment and serving
Optimize AI model inference
Scale recommendation and embedding-generation models
Work with distributed systems and big data processing
Collaborate with cross-functional teams
Stay current with AI/ML trends
What you’ll need
Strong programming in Python and Java
Experience with distributed systems and big data frameworks (Spark, Flink, Ray)
Familiarity with ML frameworks (TensorFlow, PyTorch, etc.)
2+ years of software development experience or MS/PhD equivalent
Proven track record of operating highly-available systems
Adaptability to evolving AI tools
Original job description
Snap Inc. is hiring a Software Engineer for its Core Inference team within the core ML Platform organization. The role builds and operates machine learning infrastructure for deploying, optimizing, hosting, and serving recommendation models, embedding-generation models, and self-hosted large language models at scale.Strong programming skills in Python,…