Executive Director, ML Systems & Real-Time Inference

J.P. Morgan; New York (NY); On-site; USD 180,000 - 260,000; Full time

Job summary

JPMorgan Chase in New York is seeking a Senior MLOps engineer to collaborate with data scientists, building and deploying ML models on a modern MLOps stack within a controlled enterprise environment.

You will lead real-time and batch serving, scale hyper-parameter tuning, and implement monitoring across GPU clusters and vector databases, leveraging AWS and Ray/vLLM to deliver high-performance personalization features.

Qualifications

• BS in Computer Science or related field with 10+ years of experience or MS with 6+ years of experience.
• Solid knowledge and extensive experience in Python or in cloud computing and AWS.
• Understanding of quantization techniques such as PTQ, AWQ used to quantize LLMs for accelerat ing inference on specific GPU architectures
• Solid understanding of Transformer models and challenges involved in serving large transformer-based models
• Solid understanding of ML training, especially reinforcement learning algorithms such as GRPO and DAPO
• Experience in systems engineering fundamentals: caching, CUDA, autoscaling, high throughput, low latency, cross-region resilient applications
• Deep knowledge and passion for data science fundamentals, training and deploying models
• Experience in monitoring and observability tools to monitor model input/output and features stats
• Solid grounding in engineering fundamentals and analytical mindset

Responsibilities

• Build, deploy, and maintain robust pipelines for distributed training on GPU-enabled clusters to support scalable machine learning workflows.
• Develop and manage high-volume real-time and batch inference systems, ensuring optimal performance and reliability.
• Implement quantization techniques and deploy open-weight large language models (LLMs) on modern serving stacks such as vLLM on Ray to maximize efficiency and resource utilization.
• Oversee the management and optimization of vector databases to support advanced AI and machine learning applications.
• Establish and maintain comprehensive monitoring and observability pipelines to ensure system health, performance, and rapid issue resolution.
• Collaborate with cross-functional teams to integrate new technologies and continuously improve existing infrastructure.
• Partner with product, architecture, and other engineering teams to define scalable and performant technical solutions.

Skills

Python

AWS

Distributed training

Real-time inference

MLOps

Ray

Kubernetes

LLMs

Model monitoring

Education

Bachelor's degree in Computer Science or related Engineering

Tools

Docker ecosystem

Ray

vLLM

CUDA

GPU orchestration

Job description

JPMorgan Chase in New York is seeking a Senior MLOps engineer to collaborate with data scientists, building and deploying ML models on a modern MLOps stack within a controlled enterprise environment.

You will lead real-time and batch serving, scale hyper-parameter tuning, and implement monitoring across GPU clusters and vector databases, leveraging AWS and Ray/vLLM to deliver high-performance personalization features.