Lead Software Engineer - AI/ML Deep Learning & GPU ML Serving

Be an integral part of an agile team that’s constantly pushing the envelope to enhance, build, and deliver top-notch technology products.

As a Lead Software Engineer at JPMorgan Chase within the Commercial and Investment Banking team, you will play a pivotal role in an agile team, enhancing and delivering secure, stable, and scalable technology products. As a core technical contributor, you will drive critical technology solutions across multiple technical areas, supporting the firm’s business objectives., * Lead the design, development, and troubleshooting of software solutions, applying innovative approaches to complex technical challenges.

• Write secure, high-quality production code and maintain algorithms integrated with firm systems.
• Produce architecture and design artifacts for advanced applications, ensuring compliance with design constraints.
• Analyze and visualize large, diverse data sets to improve software applications and systems.
• Identify and resolve hidden issues and patterns in data to enhance code quality and system architecture.
• Collaborate with software engineering communities to explore and adopt emerging technologies.
• Guide system design and architecture discussions, focusing on reliability and scalability.
• Optimize deep learning models for production inference, including quantization and batching.
• Deploy and manage GPU workloads in Kubernetes environments.
• Build scalable, low-latency systems using web services and APIs.
• Partner with product and program management teams to deliver business-driven solutions.

• Formal training or certification on software engineering concepts and 5+ years applied experience
• Professional software development experience, with emphasis on ML systems.
• Strong proficiency in Python and experience with ML frameworks (TensorFlow, PyTorch, or similar).
• Experience with cloud technologies (Docker, Kubernetes, EKS) and public clouds (AWS, GCP).
• Hands-on experience with ML model serving frameworks (TorchServe, TensorFlow Serving, Triton Inference Server).
• Experience deploying and managing GPU workloads in Kubernetes.
• Familiarity with scalable, low-latency systems based on web services and APIs.
• Experience with NoSQL databases (Cassandra or equivalent) for high-throughput data access.
• Understanding of GPU resource management and cost optimization.
• Experience with modern microservices architecture.
• Ability to lead the design of large-scale systems and evaluate tradeoffs., * MS/PhD in Computer Science, Machine Learning, or a related field.
• Proficiency in Java, Python, Scala, or C++.
• Experience with graph neural networks and graph processing frameworks (DGL, PyTorch Geometric, NetworkX).
• Knowledge of GPU programming (CUDA) and performance optimization.
• Experience with model monitoring, A/B testing, and ML observability tools.
• Familiarity with MLOps tools and practices (MLflow, Kubeflow, SageMaker).
• Experience serving large-scale models and optimizing for performance.