Description

You will own the end-to-end ML model lifecycle from post-training through production, ensuring models are benchmarked, deployed, monitored, and integrated into live applications.

This role is remote.

Responsibilities

• Evaluate and benchmark ML inference frameworks to guide production decisions.
• Deploy models to GCP and integrate them into Java-based streaming pipelines.
• Own deployment automation from model handoff through live serving.
• Monitor model behavior in production and perform sampling for quality evaluation.
• Debug issues across the full stack, from inference layer to streaming pipelines.

Required Skills

• 10+ years of experience in ML inference, deployment, and quality testing.
• Experience deploying models in cloud environments, specifically Google Cloud Platform (GCP).
• Proficiency with machine learning frameworks: TensorFlow, PyTorch, or JAX.
• Ability to integrate models into Java-based systems and streaming architectures.
• Strong foundation in distributed systems for debugging and end-to-end testing.
• Core ML knowledge sufficient to benchmark models and collaborate with researchers.
• Demonstrated ability to ramp up quickly on new and unfamiliar tech stacks.

Preferred Skills

• Exposure to hybrid cloud or on-premise infrastructure environments.
• Familiarity with JVM-based systems and streaming data architectures.

Key Skills

Education

Any Graduate