Job Title

As a Software Development Engineer in the MLOps Team, you will develop the blueprint for highly scalable and performant ML model serving. Role Value: As a Software Engineer (SDE III), you will design and implement robust ML infrastructure for model deployment, serving, and optimization. You will work on efficient CI/CD pipelines for ML models and leverage advanced compilers or hardware optimization to maximize inference performance while optimizing costs. We welcome you to challenge us to impact our software development processes and tools.Example Responsibilities: Build and optimize model serving infrastructure with a focus on inference latency and cost optimizationArchitect efficient inference pipelines that balance latency, throughput, and cost across various acceleration optionsDevelop monitoring and observability solutions for ML systemsCollaborate with ML Engineers to establish best practices for optimized model deploymentImplement cost-efficient, enterprise-scale solutionsCollaborate in a cross-functional, distributed team for continuous system improvementWork with MLEs, QA Engineers, and DevOps EngineersEvaluate and implement new technologies and toolsContribute to architectural decisions for distributed ML systems Experience and Qualifications:5+ years of experience in software engineering with PythonExperience with ML frameworks, particularly PyTorchExperience optimizing ML models with hardware acceleration (AWS Neuron , ONNX, TensorRT)Experience with AWS ML services and hardware-accelerated instances (Sagemaker, Inferentia, Trainium)Proven experience building and operating AWS serverless architecturesDeep understanding of event-driven processing patterns, SQS/SNS and serverless caching solutionsExperience with containerization using Docker and orchestration toolsStrong knowledge of RESTful API design and implementationProficiency in writing good quality & secure code and be familiar with static code analysis toolsExcellent analytical, conceptual and communication skills in spoken and written EnglishExperience applying Computer Science fundamentals in algorithm design, problem solving, and complexity analysis