Senior AL/ML Ops Engineer (Hybrid in Bangalore)
Smartsheet8 months ago
Bengaluru, IndiaSenior
Responsibilities
- Design, develop, and oversee the architecture and strategy for scalable and reliable AI/ML Ops platforms and pipelines.
- Package and deploy reproducible and interpretable AI/ML services to production.
- Design and implement automated CI/CD pipelines for model deployment.
- Provision and optimize training and model-serving infrastructure using Docker, Kubernetes, or serverless platforms.
- Implement post-deployment monitoring for model performance, data drift, and latency; Monte Carlo experience is preferred.
- Automate retraining and data pipeline workflows.
- Manage foundation model deployment, fine-tuning workflows, and RAG stacks involving vector databases and knowledge graphs; AWS Bedrock experience is preferred.
- Optimize GPU and CPU utilization to reduce cloud costs while maintaining low-latency inference.
- Collaborate with data scientists, data engineers, and software engineers to connect model development with production.
- Manage data, code, and model versioning using tools such as MLflow.
- Implement data security measures, governance compliance, and protection for sensitive data.
- Evaluate emerging data technologies, troubleshoot complex data-platform issues, and maintain platform stability and reliability.
Requirements
- Experience with enterprise SaaS software solutions requiring high availability and scalability.
- Experience handling large-scale structured and unstructured data from varied sources.
- Experience building and maintaining scalable, reliable, efficient, and secure AI/ML Ops platforms.
- Experience with system design, AI/ML frameworks, and large-scale data in the Databricks Lakehouse ecosystem.
- Experience with Databricks AI/ML Ops workflows, MLflow, Mosaic AI Agent Framework, Unity Catalog, Vector Search, and Knowledge Graph.
- Knowledge of LangChain and LangGraph for AI/ML Ops pipeline integration.
- Hands-on experience with at least one major cloud provider: AWS, Azure, or GCP; AWS-hosted data platform experience is preferred.
- Programming experience with Python and SQL.
- Experience with Kubernetes, CI/CD, infrastructure-as-code tools, observability, monitoring, and alerting; Terraform is preferred.
- Experience with solution cost optimization and design-to-cost practices.
- Legally eligible to work in India on an ongoing basis.
Benefits
- Hybrid work arrangement in Bangalore
Tech Stack
Categories
About Smartsheet
Smartsheet builds a cloud-based enterprise work management platform for project and portfolio tracking, automation, reporting, and collaboration used by business and IT teams. It sells SaaS subscriptions with premium capabilities and add-ons, and integrates with tools like Microsoft 365, Google Workspace, and Slack. Founded in 2005 and headquartered in Bellevue, Washington, Smartsheet is publicly traded on the NYSE (SMAR) and owns Brandfolder, a digital asset management product.