Platform ML Engineer New Jersey or Remote

Neurex AI Limited; New Jersey; Hybrid; Full time

Benefits offered by this job

High ownership and autonomy

Real impact in healthcare

Direct collaboration with founders and leadership

Job summary

A leading healthcare AI company is seeking engineers to build foundational ML infrastructure for healthcare applications. The role involves designing scalable ML systems, optimizing performance, and collaborating with product teams. Candidates should have a strong background in ML systems, experience with model serving frameworks such as TensorFlow Serving, and comfort with cloud platforms like AWS and GCP. This position offers high ownership and the opportunity to make real impacts in healthcare.

Qualifications

• Strong foundation in ML systems and infrastructure.
• Experience with model serving frameworks (TensorFlow Serving, Triton).
• Comfortable with cloud infrastructure (AWS, GCP) and Kubernetes.
• Experience with data pipelines and distributed systems.
• Familiarity with MLOps practices and tooling.

Responsibilities

• Design and build scalable ML training and inference infrastructure.
• Implement model serving systems for low-latency healthcare applications.
• Build data pipelines for training and evaluation datasets.
• Create monitoring and observability systems for ML models in production.
• Optimize model performance for cost and latency requirements.
• Work with research and product teams to deploy new models.

Skills

Strong foundation in ML systems and infrastructure

Experience with model serving frameworks

Comfortable with cloud infrastructure

Experience with data pipelines

Familiarity with MLOps practices

Clear communicator

Tools

TensorFlow Serving

Triton

AWS

GCP

Kubernetes

Job description

Build the infrastructure that powers healthcare AI at scale.

New Jersey or Remote Research & Development Full-Time

Neurex AI is building applied AI systems that operate inside real healthcare workflows. This role is for engineers who want to build the foundational ML infrastructure that enables healthcare AI at scale.

You will design and implement systems that train, deploy, and monitor ML models across production healthcare environments.

What You Will Do

• Design and build scalable ML training and inference infrastructure
• Implement model serving systems for low-latency healthcare applications
• Build data pipelines for training and evaluation datasets
• Create monitoring and observability systems for ML models in production
• Optimize model performance for cost and latency requirements
• Work with research and product teams to deploy new models

What You Will Build

• Model training pipelines with experiment tracking and versioning
• Real-time and batch inference systems for healthcare AI
• Feature stores and data management infrastructure
• Model monitoring and drift detection systems
• HIPAA-compliant ML infrastructure with security guardrails

Who You Are

• Strong foundation in ML systems and infrastructure
• Experience with model serving frameworks (TensorFlow Serving, Triton, etc.)
• Comfortable with cloud infrastructure (AWS, GCP) and Kubernetes
• Experience with data pipelines and distributed systems
• Familiarity with MLOps practices and tooling
• Clear communicator with high standards

Why Neurex AI

• AI that is deployed, not demoed
• High ownership and autonomy
• Real impact in healthcare
• Opportunity to shape products, systems, and culture
• Direct collaboration with founders and senior leadership