SDE III MLOps

Role Purpose

As an SDE III in the MLOps team, you will help build the foundation for highly scalable, reliable, and high-performance ML model serving. Youll be responsible for designing systems that support the entire lifecycle of ML modelsfrom data to deployment—ensuring seamless operations and efficient workflows.

Role Value

In this role, you will drive continuous improvement across ML infrastructure and applications, enhancing developer experience and strengthening governance of ML assets (data + models).
You will design and implement robust ML deployment pipelines, model-serving systems, and automation frameworks. You’ll work with cutting-edge optimization techniques, compilers, and hardware accelerators to deliver fast, cost-efficient inference at scale.

This role empowers you to shape engineering practices, propose innovations, and influence architectural decisions for distributed ML systems.

Key Responsibilities

• Enhance ML asset management systems (models & datasets) for scalability, governance, and developer efficiency.
  
• Build and optimize model-serving infrastructure with a strong focus on low latency, high throughput, and cost optimization.
  
• Architect efficient inference pipelines using modern acceleration options.
  
• Implement cost-efficient, production-grade ML systems.
  
• Collaborate with cross-functional teams—MLEs, QA, DevOps—to ensure reliable ML delivery.
  
• Evaluate and integrate new tools, technologies, and frameworks.
  
• Contribute to architectural decisions for distributed, enterprise-scale ML systems.
  

Experience & Qualifications

• 5+ years of software engineering experience (Python required).
  
• Strong hands-on experience with model lifecycle management (MLflow, Weights & Biases, etc.).
  
• Experience with data quality, transformation pipelines, and data cataloging.
  
• Proficiency with ML frameworks, especially

  PyTorch

  .
• Experience optimizing ML models using

  AWS Neuron, ONNX, TensorRT, or similar accelerators

  .
• Proven expertise in building and operating

  AWS serverless architectures

  .
• Understanding of event-driven architectures (SQS/SNS) and serverless caching.
  
• Experience with Docker and container orchestration.
  
• Strong knowledge of RESTful API design and development.
  
• Ability to write high-quality, secure code; familiarity with static analysis tools.
  
• Strong analytical, conceptual, and communication skills.
  
• Solid foundation in algorithms, problem-solving, and system design.
  

Nice to Have

• Experience with model compilation, quantization, and inference performance benchmarking.
  
• Experience supporting ML systems in regulated or compliance-heavy environments.