Machine Learning Engineer

Core Responsibilities:

• Develop and enhance AI services including AI Insights pilot and AI Automated Answers using LLM/RAG architectures.
• Maintain and optimize our mission-critical Machine Moderation system using Python-based NLP models deployed on AWS (Lambda, ECS, SageMaker, SQS, SNS).
• Train, evaluate, and monitor machine learning models using orchestration tools (e.g. Flyte, Airflow).
• Manage ML pipelines on AWS with containerized services and CI/CD deployment via GitHub Actions.
• Implement streaming data processing using Kafka for real-time content moderation decisions.
• Monitor model performance and drift using observability tools (e.g. Arize AI).
• Collaborate with teams using Scala-based services and maintain API integrations for model serving.
• Conduct architectural reviews for ML pipeline design and Infrastructure as Code (Terraform).
• Research and implement novel LLM & NLP approaches for content moderation and consumer insights.
• Optimize batch and streaming ML workloads processing millions of reviews, questions, and answers daily.

Technical Requirements:

• Strong Python proficiency for ML model development and deployment.
• Experience with AWS cloud services (Lambda, ECS, ECR, SageMaker, MSK, SNS, SQS).
• Familiarity with ML orchestration platforms and CI/CD pipelines.
• Knowledge of streaming technologies (Kafka) and high-volume data processing.
• Experience with NLP, LLMs, and production ML monitoring tools.
• Ideally with strong a Software Engineering or Computer Science background.
• Willingness to work with Scala-based systems and learn as needed.

Key Technical Areas:

• Production ML system maintenance using cloud-native AWS infrastructure.
• Real-time and batch model serving with monitoring and alerting.
• Cross-functional API development and integration with existing services.
• Research and development of NLP applications for e-commerce content analysis.