Software Engineer - AI/ML GPU Serving
Core
Design, develop, and maintain scalable ML systems and services, including GPU workloads and model serving, within a secure banking environment.
Role type
Senior IC software engineer (AI/ML GPU serving)
Builds
Scalable web services, APIs, and ML model serving infrastructure
Domain
Financial services / Machine Learning / Cloud Infrastructure
Required skills
Python, TensorFlow, PyTorch, Docker, Kubernetes, AWS, GCP, NoSQL (Cassandra), System Design, Distributed Systems, Microservices, AI-assisted development tool usage, Responsible AI practices
Preferred skills
Java, C++, GPU workload deployment, ML model serving frameworks (TorchServe, TensorFlow Serving, Triton), Distributed training/inference, Model compression, Edge deployment, API management, Domain-Driven Design
Technologies
AI API, AWS, Cassandra, Docker, GCP, Java, Kubernetes, PyTorch, Python, TensorFlow, TorchServe, Triton Inference Server
Responsibilities
Design and build scalable systems and services such as web services and APIs; Create secure, high-quality production code and maintain algorithms; Use enterprise-authorized AI coding assistance tools to improve code quality while validating results; Produce architecture and design artifacts for complex applications; Gather, analyze, and synthesize large, diverse data sets to support continuous improvement; Proactively identify hidden issues and patterns in data to improve coding hygiene and system architecture
Seniority
Senior, hands-on IC