Responsibilities :

- Upgrade ML asset (model, data) management systems for better developer experience and robust governance capabilities.

- Build and optimize model serving infrastructure with a focus on inference latency and cost optimization.

- Architect efficient inference pipelines that balance latency, throughput, and cost across various acceleration options.

- Implement cost-efficient, enterprise-scale solutions.

- Collaborate in a cross-functional, distributed team for continuous system improvement.

- Work with MLEs, QA Engineers, and DevOps Engineers.

- Evaluate and implement new technologies and tools.

- Contribute to architectural decisions for distributed ML systems.

Requirements :

- 5+ years of experience in software engineering with Python.

- Experience with model lifecycle management (MLFlow, Weights and Biases, or equivalent).

- Experience with a data management ecosystem (quality, transformation, and catalog).

- Experience with ML frameworks, particularly PyTorch.

- Experience optimizing ML models with hardware acceleration (AWS Neuron, ONNX, TensorRT).

- Proven experience building and operating AWS serverless architectures.

- Deep understanding of event-driven processing patterns, SQS/SNS and serverless caching solutions.

- Experience with containerization using Docker and orchestration tools.

- Strong knowledge of RESTful API design and implementation.

- Proficiency in writing good-quality and secure code and being familiar with static code analysis tools.

- Excellent analytical, conceptual, and communication skills in spoken and written English.

- Experience applying Computer Science fundamentals in algorithm design, problem solving, and complexity analysis.

Great to have Experience and Qualifications :

- Experience with any of the following : model compilation and quantization, performance profiling, and benchmarking ML inference systems.

- Experience working in regulated industries with strict compliance requirements for cloud-native solutions.