Senior Machine Learning Engineer (Inference Platform)

Role Overview

Join Wizard as a Senior Machine Learning Engineer (Inference Platform). You will own the end-to-end lifecycle of production ML systems, working closely with ML, Data, and DevOps teams to bring models from experimentation into reliable, scalable services.

Key Missions & Responsibilities

• Own the end-to-end lifecycle of ML systems, including:
  • Packaging, deployment, monitoring, and scaling
• Build and improve production ML pipelines, enabling a smooth transition from experimentation to production use
• Define and monitor system metrics to improve performance and ensure systems are:
  • Resilient
  • Cost-aware
• Design resilient, cost-aware inference systems by applying strong engineering practices to ML workflows
• Partner across teams to turn ideas into production-ready systems

Requirements

• Strong Python skills and a solid foundation in software engineering
• Experience (or strong curiosity) with systems that serve different model types under different constraints
• Comfort operating in a fast-moving environment where requirements evolve quickly
• Solid understanding of inference performance, including:
  • batching
  • memory usage
  • quantization
  • CPU vs GPU behavior
• Experience deploying and running LLMs (or other deep learning models) in real-world environments
• Ability to reason about tradeoffs between speed, cost, and reliability
• Familiarity with cloud platforms and common ML tooling (e.g., model registries, experiment tracking)
• 5–8+ years of experience in software/ML/platform/infrastructure engineering with hands-on ownership of production ML systems

Nice-to-Haves (implied)

• Experience with specific cloud environments: AWS, GCP, or Azure