Engine is looking to enhance the performance of their pricing strategies by incorporating ML models into their flow to balance turning a profit, passing savings along to members, and remaining competitive within the market.
Requirements
- Hands-on with TensorFlow Serving, TorchServe, or similar frameworks
- Python, gRPC & REST – Build production-grade APIs and integrate model inference into application workflows
- Docker & Kubernetes – Containerize and orchestrate inference services at scale
- Argo CD & Terraform – Manage deployments and infrastructure via GitOps and IaC
- Datadog, Prometheus, OpenTelemetry – Instrument, monitor, and alert on system health
- CI/CD – Automate versioning, testing, and promotion of model-serving pipelines
- Feature Delivery & Model Lifecycle – Experience wiring real-time features (e.g., Redis, Kafka) and managing model versions with tools like MLflow or BentoML
Responsibilities
- Deploy and operate machine learning models optimized for low-latency, high-throughput inference in production environments
- Build and maintain clean gRPC interfaces to expose model predictions to upstream services
- Own the production code paths that deliver features to the model—writing maintainable, testable application logic that integrates cleanly with the broader system
- Implement caching, circuit breakers and graceful fallbacks to isolate ML failures
- Tackle cold-start issues, batching strategies, serialization overhead, and memory management
- Instrument metrics (latency, throughput, error rates); configure autoscaling and alerting
- Containerize workloads, automate promotions across dev/staging/prod, and manage side-by-side model versions with clear rollback mechanisms
Other
- Competitive base pay tied to role and experience, with opportunities for bonuses, commissions, and equity
- Benefits: Check out our full list at engine.com/culture
- Environments for Success: Different roles have different needs in terms of the environments that drive success which is why we have a hybrid-hub model