Senior ML Infra Engineer - Scalable Model Serving (Remote)

Etsy, Inc.; New York (NY); Hybrid; USD 182,000 - 246,000; Full time

Benefits offered by this job

Equity package

Annual bonus

Comprehensive benefits

Job summary

Etsy is seeking a Senior Software Engineer, Machine Learning to build and operate the infrastructure that trains, hosts, and serves its ML models, including a growing portfolio of predictive and generative tools. You will design scalable serving endpoints and collaborate with Applied Scientists to remove friction in model workflows.

Based in the ML Enablement team, you will work on architecture, deployment tooling, and reliability to support millions of inferences per second using Python and

Qualifications

• Bachelor's degree in CS or related field or equivalent experience.
• 5+ years building and troubleshooting complex backend systems.
• Proficient Python with production-grade experience.
• Hands-on cloud infra and Kubernetes for production workloads.
• Familiar with observability tooling for distributed systems.
• Working knowledge of ML fundamentals and hosting open-source models.
• Understanding of transformer architectures and serving implications.
• Comfort with large-scale, high-availability infrastructure design.

Responsibilities

• Write high-quality production-grade Python code and participate in reviews.
• Build, operate, and improve infra for training and serving ML models.
• Design serving infra for open-source and internal LLMs; manage deployment.
• Apply ML fundamentals to inform infrastructure decisions.
• Collaborate with Applied Scientists to align needs with infrastructure.
• Contribute to system design decisions prioritizing performance and reliability.

Skills

Python

Distributed systems

Cloud infra

LLM serving

Transformer architectures

Observability

Education

Bachelor's degree in Computer Science or related field

Tools

Kubernetes

Google Cloud

Job description

Etsy is seeking a Senior Software Engineer, Machine Learning to build and operate the infrastructure that trains, hosts, and serves its ML models, including a growing portfolio of predictive and generative tools. You will design scalable serving endpoints and collaborate with Applied Scientists to remove friction in model workflows.

Based in the ML Enablement team, you will work on architecture, deployment tooling, and reliability to support millions of inferences per second using Python and