Staff MLOps Engineer - USA

Job Description

Inworld, a leading AI technology provider, is seeking a Staff Platform Engineer (MLOps) to join their team. This role involves working closely with backend and ML Engineering teams to design, deploy, and maintain reliable, high-performance, and secure cloud infrastructure for Inworld's AI Engine and Studio. The ideal candidate will facilitate a "you build it, you run it" culture by providing the necessary tools and processes for monitoring service reliability, availability, and performance.Role involves:

• Developing, managing, and optimizing the ML model lifecycle in production.
• Implementing CI/CD systems for ML workflows.
• Monitoring models to identify issues and inefficiencies.
• Designing MLOps tools and frameworks to enhance automation and efficiency.
• Managing CI/CD pipelines to ensure smooth and efficient code integration and deployment.
• Identifying and implementing opportunities to enhance engineering speed and efficiency.
• Conducting root cause analysis to identify critical issues and develop automated solutions.
• Developing and sharing best practices to improve automation and efficiency across engineering teams.

Requirements:

• 7 years of experience in software engineering.
• 5 years of experience with infrastructure-as-code.
• Proficiency in managing Kubernetes clusters and applications.
• Experience in creating and maintaining CI/CD pipelines.
• Deep knowledge of at least one major cloud provider (GCP, Azure, Oracle Cloud).
• Proficiency in at least one backend programming/scripting language (Golang, Python, Bash).
• Familiarity with open source LLM and open source serving solution (e.g. vLLM or llama.cpp, kserve, etc) is a plus.
• Experience with SLURM
• Experience with data pipeline and workflow management tools

Inworld offers:

• A hybrid work environment based in Mountain View, CA.
• Equity and benefits.