MLOps Engineer (SDE 3)

Key Responsibilities

• Build and optimize ML model serving infrastructure with a focus on low-latency, cost-efficient inference.
• Architect scalable inference pipelines balancing latency, throughput, and infrastructure cost.
• Develop monitoring, logging, and observability solutions for production ML systems.
• Collaborate with ML Engineers to establish best practices for model deployment and inference optimization.
• Design and implement enterprise-scale, cost-optimized ML infrastructure.
• Work closely with MLEs, QA Engineers, DevOps Engineers, and cross-functional teams.
• Evaluate, benchmark, and adopt new ML infrastructure technologies and tools.
• Contribute to architecture and design decisions for distributed ML systems.

Mandatory Skills & Experience

• 5+ years of software engineering experience with Python.
• Strong hands-on experience with PyTorch.
• Experience optimizing ML models using AWS Neuron, ONNX, and TensorRT.
• Hands-on experience with AWS SageMaker, Inferentia, and Trainium.
• Experience building and operating AWS serverless architectures.
• Strong understanding of event-driven architectures using SQS, SNS, and serverless caching.
• Experience with Docker and container orchestration.
• Strong knowledge of RESTful API design and development.
• Experience writing secure, high-quality, production-grade code and using static code analysis tools.
• Strong understanding of algorithms, data structures, problem-solving, and complexity analysis.
• Excellent verbal and written communication skills.