About the job
This is a role of a Sr Software Engineer who has deep systems thinking to design, build, and enhance a scalable and highly concurrent ML/AI serving platform. Knowledge of Python, Machine Learning concepts, tools, and packages is a must. If you’re excited about building a production-grade platform and solving hard distributed systems problems, this is your opportunity to make a lasting impact at scale.
Responsibilities
You will design and implement large-scale, secure, and highly available systems, while collaborating across teams to drive the future of secure, scalable inference platforms. The mindset required and to be developed is how to process thousands of transactions per second, how to achieve consistency without sacrificing performance. Work with cross-functional teams to drive requirements, size scope and effort, mentor junior engineers, lead the project to completion, and provide support for any production issues.
Qualifications
Minimum
8+ years of software development experience
4+ years of Python expertise building production applications
Solid understanding of Python concurrency, threading, multiprocessing, and their practical trade-offs in high-throughput production systems
Strong understanding of Python internals and their implications in highly concurrent systems
Deep knowledge of ML/AI frameworks and ecosystems
Strong understanding of computer science fundamentals, including data structures and algorithms
Proficiency in containerization technologies like Kubernetes and CNCF technologies
Proficiency in profiling, optimizing, debugging Python applications and libraries
Bachelor’s Science Computer Science or equivalent or a similar discipline degree or experience
Preferred
Excellent written and verbal communication skills on both technical and non-technical topics
Experience building async web services with Gunicorn (Green Unicorn), FastAPI, or other Python frameworks
Exposure to Ray, KServe, Triton, or other inference frameworks
Ability to debug complex cross-platform issues and optimize performance
Ability to debug and improve ML workflow tuning for high accuracy
Knowledge of using GenAI to build solutions to improve productivity of developers, users, and businesses
Self-directed, self-motivated, and detail-oriented with the ability to come up with good design proposals and thorough analysis of production issues