Senior MLOps Engineer - Full Time - no 3rd parties

100% remote role - work on EST

We are seeking a Senior MLOps Engineer to support large-scale production machine learning environments focused on text, image, and video processing workloads in AWS.

This is a highly operational and infrastructure-focused role. The ideal candidate has hands-on experience deploying, monitoring, scaling, and optimizing ML systems in production environments particularly within AWS SageMaker ecosystems.

This is NOT a data science or model research role. The focus is production reliability, deployment governance, infrastructure scalability, observability, and operational efficiency.

Responsibilities

ML Deployment & Operations

• Design, deploy, and support end-to-end production ML pipelines
• Manage ML promotion across Dev, QA, and Production environments
• Implement deployment standards, rollback strategies, and recovery mechanisms
• Support containerized inference and orchestration patterns

AWS & Infrastructure Management

• Configure and manage AWS SageMaker pipelines, endpoints, and monitoring
• Optimize GPU and CPU infrastructure selection and scaling
• Benchmark infrastructure performance and tune autoscaling behavior
• Perform load testing and production infrastructure optimization

Monitoring & Reliability

• Implement monitoring, alerting, observability, and drift detection
• Track latency, throughput, error rates, and model/data drift
• Build A/B testing and controlled rollout frameworks
• Ensure governance, reproducibility, security, and cost efficiency

Large-Scale ML Workloads

• Support production ML systems across text, image, and video workloads
• Manage high-throughput infrastructure and large-scale data movement
• Prevent compute, networking, and storage bottlenecks
• Support systems processing hundreds of thousands of requests daily

Collaboration

• Partner closely with ML Engineers, Platform Engineering, DevOps, and Data teams
• Operationalize ML models into stable production systems
• Help drive scalability, reliability, and infrastructure best practices

Required Qualifications

• Strong hands-on experience operating production ML systems at scale
• Deep AWS SageMaker experience including:
  • Pipelines
  • Endpoints
  • Monitoring
  • Multi-environment deployments
• Experience operationalizing PyTorch and TensorFlow models
• Experience with containerized ML deployment and orchestration
• Experience optimizing GPU/CPU infrastructure for ML workloads
• Strong monitoring and observability experience
• Experience implementing deployment governance and rollback strategies

Strongly Preferred

• Experience supporting:
  • Transformer-based NLP systems
  • Computer vision workloads
  • Ranking/reranking systems
• Familiarity with:
  • ANN systems
  • HNSW indexing
  • Large-scale neural network operational workloads
• Experience supporting high-volume text, image, and video dataset
• Candidates must be able to work directly on W2 or approved independent consulting arrangements.

• NO 3RD PARTY FIRMS, LAYERED VENDORS, OR STAFFING PASSTHROUGHS.
• Third-party submissions will NOT be reviewed or responded to.

If interested, please send:

• Updated resume
• Current location
• Work authorization status
• Availability
• Salary expectations