AI / MLOps Engineer

About This Role

Manage operational workflows for AI/ML model deployments and monitor their performance across multi-cloud environments. Track and optimize cloud spend for AI/ML operations and build dashboards for key performance indicators.

Responsibilities

• Manage operational workflows for model deployments, updates, and versioning across GCP, Azure, and AWS
• Monitor model performance metrics: latency, throughput, error rates, token usage, and inference quality
• Track model drift, accuracy degradation, and performance anomalies, escalating to engineering as needed
• Support knowledge base operations including vector embedding pipeline health, chunk quality, and refresh cycles in Vertex AI
• Maintain model inventory and documentation across multi-cloud environments
• Coordinate model evaluation cycles with Responsible AI and Core Engineering teams
• Monitor AI agent health, performance, and reliability and support their deployment and configuration management
• Track and analyze AI/ML cloud spend across GCP (Vertex AI), Azure (OpenAI), and AWS (Bedrock)
• Build and maintain dashboards for platform performance, model health, agent metrics, and operational KPIs
• Support release management processes with pre/post-deployment validation checks and track release health metrics

Requirements

• 2-4 years in an Ops, Analytics, or Technical Operations role (MLOps, AIOps, DataOps, Platform Ops, or similar)
• Understanding of AI/ML concepts: models, inference, embeddings, vector databases, LLMs, tokens, prompts
• Experience with cloud cost management and FinOps
• Strong proficiency with dashboarding and visualization tools (Looker, Tableau, Grafana, or similar)
• Working knowledge of GCP
• Comfortable with SQL and basic Python for data analysis and scripting
• Experience with monitoring and observability platforms (Datadog, Prometheus/Grafana, Cloud Monitoring, or similar)
• Understanding of APIs and API gateways
• Strong analytical and problem-solving skills
• Excellent communication skills

Qualifications

• College degree in Computer Science, BIS, MIS, EE, ME or similar
• 2-4 years in an Ops, Analytics, or Technical Operations role (MLOps, AIOps, DataOps, Platform Ops, or similar)

Nice to Have

• Hands-on experience with LLM platforms: Vertex AI, Azure OpenAI, AWS Bedrock
• Familiarity with AI agents and agentic architectures (AutoGen, LangChain, or similar)
• Exposure to MCP (Model Context Protocol) or agent-tool integration patterns
• Experience with vector databases and RAG (Retrieval-Augmented Generation) operations
• Understanding of MLOps lifecycle
• Experience with APIGEE or similar API management platforms
• Familiarity with Responsible AI metrics
• FinOps certification or formal cloud cost management experience
• Experience supporting enterprise platform teams with multiple consuming applications
• Familiarity with ML pipeline tools (Kubeflow, MLflow, Vertex AI Pipelines)
• Exposure to prompt management and evaluation frameworks
• ITIL or operational process framework experience
• Experience creating runbooks and operational documentation

Skills

* Required skills