Lead ML Engineer: Real-Time Personalization & AI Pipelines

Fairygodboss; New York (NY); On-site; USD 180,000 - 260,000; Full time

Benefits offered by this job

Health care coverage

On-site health centers

Retirement savings plan

Tuition reimbursement

Mental health support

Job summary

JPMorgan Chase & Co. seeks a senior MLOps engineer to collaborate with data scientists, building and deploying ML models on a modern MLOps stack. Lead on the Recommendation Engine team, crafting pipelines for distributed training and real-time inference on GPU clusters in AWS.

You will quantize models, manage vector databases, and maintain observability pipelines while working with product and architecture to deliver scalable solutions.

Qualifications

• BS in CS or related Engineering with 6+ years experience or MS with 4+ years experience.
• Strong Python and cloud computing experience, preferably AWS.
• Experience with quantization techniques (PTQ, AWQ) for LLMs to accelerate inference.
• Solid systems engineering fundamentals: caching, CUDA, autoscaling, high throughput, low latency.

Responsibilities

• Build, deploy, and maintain robust pipelines for distributed training on GPU-enabled clusters.
• Develop and manage pipelines for high-throughput real-time and batch inference.
• Implement quantization techniques and deploy large language models for efficient inference.
• Oversee vector databases to support advanced AI/ML applications.
• Establish and maintain monitoring and observability pipelines for system health and performance.
• Collaborate with cross-functional teams to integrate new technologies and improve infrastructure.
• Partner with product, architecture, and engineering teams to define scalable solutions.

Skills

Python

AWS

LLM quantization

CUDA

Distributed training

Monitoring & observability

Containers/Docker

Kubernetes

Airflow/Kubeflow

Ray/Spark

Education

BS in Computer Science or related Engineering (6+ years)

MS in Computer Science or related Engineering (4+ years)

Tools

Ray

DuckDB

Spark

Docker

Kubernetes

ECS

Airflow

Kubeflow

vllm/SGLang

Job description

JPMorgan Chase & Co. seeks a senior MLOps engineer to collaborate with data scientists, building and deploying ML models on a modern MLOps stack. Lead on the Recommendation Engine team, crafting pipelines for distributed training and real-time inference on GPU clusters in AWS.

You will quantize models, manage vector databases, and maintain observability pipelines while working with product and architecture to deliver scalable solutions.