Lead Machine Learning Engineer-MLOps

Lead Machine Learning Engineer-MLOps on JPMorganChase's Recommendation Engine team, building and deploying ML models on a modern MLOps stack onsite in Palo Alto, CA.

Responsibilities

• Design, implement, and sustain end-to-end pipelines for distributed training on GPU-accelerated clusters to enable scalable ML workflows.
• Create and operate pipelines for high-throughput real-time and batch inference, prioritizing performance and reliability.
• Apply quantization approaches and deploy large language models to improve efficiency and resource utilization.
• Manage and optimize vector databases to support advanced AI and ML applications.
• Build 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 enhance existing infrastructure.
• Coordinate with product, architecture, and other engineering teams to define scalable, high-performance technical solutions.

Requirements

• BS in Computer Science or related Engineering field with 6+ years of experience.
• MS in Computer Science or related Engineering field with 4+ years of experience.
• Strong Python proficiency and cloud computing experience, ideally AWS.
• Understanding of quantization techniques such as PTQ and AWQ used to accelerate LLM inference on specific GPU architectures.
• Foundations in systems engineering including caching, CUDA, autoscaling, high throughput, low latency, and cross-region resilience.
• Solid grounding in data science concepts and hands-on experience training and deploying models.
• Experience with monitoring and observability tools to track model inputs, outputs, and feature statistics.
• Operational experience with big data and ML tools such as Ray, DuckDB, Spark, and with training and inference systems like Ray and vLLM/SGLang.
• Strong engineering fundamentals and an analytical mindset.

Technologies

• Python
• AWS
• CUDA
• PTQ
• AWQ
• Ray
• DuckDB
• Spark
• vllm
• SGLang
• Docker
• Kubernetes
• ECS
• Airflow
• Kubeflow
• vector databases

Benefits

• Base salary range: USD 164,350 - 260,000 per year.
• Commission-based pay and/or discretionary incentive compensation, paid in cash and/or forfeitable equity, awarded for individual achievements and contributions.
• Comprehensive health care coverage
• On-site health and wellness centers
• Retirement savings plan
• Backup childcare
• Tuition reimbursement
• Mental health support
• Financial coaching