Scala Senior Software Engineer I, Machine Learning, ML Enablement

Etsy•New York, NY

1d•$164,000 - $246,000•Hybrid

About The Position

Etsy is hiring a Senior Software Engineer for its Machine Learning Enablement initiative. The role builds and operates infrastructure for training, hosting, and serving Etsy’s machine learning models, including its internal serving platform and predictive and generative models, such as open-source LLMs. The engineer will architect systems that make model serving fast, reliable, observable, and scalable, supporting millions of inferences per second and enabling Applied Scientists and Engineers to train, host, and iterate on models. The Models Training and Serving Platform team owns the path from a trained model to a production-ready serving endpoint. Its work spans infrastructure, deployment tooling, resource management, performance tuning, and reliability. The team partners with teams across Etsy and applies a product-driven approach to building self-service ML infrastructure. This is a full-time position reporting to the Engineering Manager. Etsy prioritizes candidates within commuting distance of its Brooklyn office, with in-office attendance once or twice per week depending on proximity. Remote candidates outside commuting distance may be considered case by case, with occasional travel to the office expected. The stated annual base salary range is $182,000–$246,000 in Geo-1 locations and $164,000–$222,000 in Geo-2 locations. The role is also eligible for equity and an annual performance bonus.

Requirements

Bachelor's degree in Computer Science, Applied Statistics, Mathematics, Electrical Engineering, or a related quantitative field, or equivalent professional experience.
At least 5 years of professional experience building, iterating on, and troubleshooting complex backend and infrastructure systems.
Strong software engineering fundamentals, including algorithms and data structures, and the ability to write production-ready Python code.
Hands-on experience with cloud infrastructure, preferably Google Cloud, and Kubernetes, including deploying and operating production workloads.
Familiarity with observability tools for metrics, logging, and tracing to monitor and debug distributed systems.
Working knowledge of machine learning fundamentals and concepts, with awareness of LLM serving infrastructure and hosting open-source models.
Basic understanding of transformer architectures, predictors, and how model design choices affect serving infrastructure.
Comfort with system design for large-scale, high-availability infrastructure.

Nice To Haves

Experience with Google Cloud is preferred.
Experience with additional programming languages is a plus.

Responsibilities

Write production-grade Python code, participate in code reviews and pair programming, and contribute to architectural decisions.
Build, operate, and improve infrastructure for training and serving machine learning models on GCP and Kubernetes, focusing on scalability, reliability, and observability.
Design and maintain serving infrastructure for open-source and internally hosted LLMs, including model deployment, resource management, and performance tuning.
Use machine learning knowledge, including deep learning, transformer architectures, prediction, and inference systems, to inform infrastructure and design decisions.
Partner with Applied Scientists to understand model training and serving needs and translate them into infrastructure that improves their workflows.
Contribute to system design discussions and balance performance, cost, and reliability for infrastructure serving more than 100 million users.
Use generative AI and other productivity tools thoughtfully to work efficiently and contribute intentionally.