
ML Systems Engineer
Posted 4 days ago

Posted 4 days ago
This is a fully remote position, open to applicants in United States.
• Design, construct, and sustain production infrastructure for machine learning systems throughout Bask Health.
• Create model-serving services that provide machine learning predictions via dependable APIs.
• Establish and manage infrastructure for both batch and real-time model inference.
• Execute automated workflows for model packaging, deployment, and version control.
• Develop reusable deployment patterns for machine learning applications.
• Create systems for overseeing model artifacts, configurations, and runtime dependencies.
• Implement continuous integration and deployment pipelines for ML services.
• Develop infrastructure that enables reproducible model releases and controlled rollbacks.
• Construct monitoring systems to track model-serving latency, throughput, errors, and availability.
• Set up logging and tracing for production machine learning services.
• Assist in model performance monitoring and identify unexpected changes in input data.
• Create data processing and feature preparation pipelines that facilitate production inference.
• Integrate machine learning services with existing backend applications and databases.
• Develop asynchronous processing systems for extensive or prolonged inference tasks.
• Optimize inference performance, resource utilization, and infrastructure costs.
• Create automated tests for model-serving APIs and infrastructure components.
• Establish safeguards for service failures, timeouts, retries, and fallback behaviors.
• Collaborate with machine learning engineers to outline deployment and operational requirements.
• Partner with applied scientists to transition validated models into production.
• Build tools that streamline model deployment and troubleshooting for engineering teams.
• Implement suitable authentication, authorization, and access controls for ML services.
• Ensure production systems adhere to tenant boundaries and approved data-handling protocols.
• Investigate infrastructure incidents and rectify production reliability issues.
• Enhance system scalability and fault tolerance as application demands increase.
• Support experimental environments and testing infrastructure for machine learning development.
• Document infrastructure architecture, deployment processes, and operational standards.
• Participate in code reviews, technical planning, and architecture discussions.
• Take ownership of designated ML infrastructure projects from design through deployment, monitoring, and ongoing improvement.
• 3+ years of professional experience in software engineering, machine learning engineering, infrastructure engineering, or a closely related technical area.
• Proven experience in building and maintaining production backend services or infrastructure.
• Strong programming proficiency in Python, TypeScript, or similar languages.
• Knowledge of machine learning development and deployment workflows.
• Experience in developing APIs and integrating backend services.
• Familiarity with cloud infrastructure and the deployment of production applications.
• Understanding the fundamentals of distributed systems and service reliability.
• Experience with automated testing and continuous integration methodologies.
• Familiarity with containerization or similar application packaging techniques.
• Comprehension of model inference and the requirements for production model serving.
• Experience working with databases and structured application data.
• Familiarity with asynchronous processing and background job systems.
• Experience implementing logging, monitoring, and operational diagnostics.
• Understanding system performance, latency, throughput, and scalability.
• Ability to troubleshoot production infrastructure and application failures.
• Familiarity with authentication, authorization, and secure service communication.
• Experience using Git and engaging in collaborative engineering workflows.
• Understanding software configuration and dependency management.
• Ability to design reusable infrastructure components and engineering tools.
• Familiarity with data processing pipelines and considerations for production data quality.
• Experience writing maintainable, well-tested production code.
• Understanding deployment automation and release management.
• Ability to assess technical trade-offs related to reliability, performance, and cost.
• Strong analytical and problem-solving capabilities.
• Ability to collaborate effectively with machine learning engineers, applied scientists, and software engineers.
• Nice to have: Experience in deploying and operating machine learning models in production.
• Nice to have: Familiarity with MLOps platforms and tools for model lifecycle management.
• Nice to have: Experience with MLflow, SageMaker, or similar machine learning infrastructure.
• Nice to have: Familiarity with model registries and artifact management systems.
• Nice to have: Experience developing real-time inference APIs.
• Nice to have: Experience with batch inference and distributed data processing.
• Nice to have: Familiarity with Docker, Kubernetes, or comparable container orchestration technologies.
• Nice to have: Experience using AWS Lambda, SQS, EventBridge, or related cloud services.
• Nice to have: Familiarity with serverless infrastructure and infrastructure-as-code tools.
• Nice to have: Experience with SST or similar application deployment frameworks.
• Nice to have: Experience in building CI/CD pipelines for machine learning applications.
• Nice to have: Familiarity with model monitoring and data drift detection.
• Nice to have: Experience with feature stores or reusable feature pipelines.
• Nice to have: Understanding model versioning, canary deployments, and rollback strategies.
• Nice to have: Familiarity with GPU-based inference or optimization of model serving.
• Nice to have: Experience supporting large language model applications or embedding services.
• Nice to have: Familiarity with vector databases and retrieval infrastructure.
• Nice to have: Experience in building internal developer platforms or reusable infrastructure libraries.
• Nice to have: Understanding of HIPAA and healthcare data privacy considerations.
• Nice to have: Experience using AI-assisted development tools like Cursor or Claude Code.
• Competitive salary and performance-based bonuses.
• Comprehensive health, dental, and vision insurance.
• Flexible working hours and remote work opportunities.
• Generous vacation and leave policies.
• Professional development and learning opportunities.
Memory Bridge
Entrada
Find Your Talent (FYT)
Inmetrics
Get handpicked remote jobs straight to your inbox weekly.