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

Lead Software Engineer role focusing on AI/ML deep learning and GPU ML serving at JPMorgan Chase. You will design, develop, and optimize production ML systems, deploying GPU workloads in Kubernetes and building scalable low-latency services.

• Lead design and development of software solutions; produce architecture artifacts; optimize deep learning models for production inference (quantization, batching); deploy and manage GPU workloads in Kubernetes; build scalable, low-latency systems using web services and APIs.

• Formal training or certification in software engineering with 5+ years experience; strong proficiency in Python and ML frameworks (TensorFlow, PyTorch); experience with Docker, Kubernetes, EKS, AWS/GCP; hands-on experience with ML model serving (TorchServe, TensorFlow Serving, Triton Inference Server); experience deploying GPU workloads in Kubernetes; familiarity with NoSQL databases (Cassandra) and microservices architecture.

• MS/PhD in Computer Science or ML; proficiency in Java, Scala, or C++; experience with graph neural networks (DGL, PyTorch Geometric, NetworkX); GPU programming (CUDA); ML observability tools; MLOps tools (MLflow, Kubeflow, SageMaker).