Own the reliability and performance of ML model inference systems in production
Ensure high availability of deployed models across APIs and enterprise products
Build systems to handle scaling, load variability, and production traffic growth
Reduce operational burden through better tooling, automation, and processes
Help define how Modulate runs ML systems at scale with reliability and efficiency
Deploy, monitor, and maintain production machine learning inference systems
Oversee fleets of inference machines and ensure system health and performance
Design monitoring, alerting, and incident response systems for ML workloads
Participate in on-call rotations and lead incident response and debugging
Build systems and processes for scaling inference infrastructure under variable load
Improve reliability and observability of production ML services
Collaborate on infrastructure-as-code for production deployments
Support or contribute to GPU-based training and inference infrastructure
Work closely with ML and engineering teams to ensure smooth model deployments
(Optional growth area) Optimize model inference performance and latency

Experience deploying and maintaining production software systems
Experience building monitoring and alerting systems for production environments
Experience with on-call rotations and incident response
Strong experience with AWS, Python, and Linux
Exposure to PyTorch or similar ML frameworks
Experience working with GPU-based applications and basic GPU tooling (drivers, runtime, monitoring)
Strong debugging and systems thinking skills
Ability to operate calmly in production incident environments
Nice to Have
Experience with ML model serving systems or dedicated model servers
Experience monitoring GPU performance for inference workloads
Experience optimizing machine learning model inference
Familiarity with audio or multimedia data (codecs, streaming, real-time systems)
Experience with infrastructure-as-code (e.g., Terraform, CloudFormation)

Machine Learning Operations Engineer

Key skills