ml engineer for AI agents

Grid Dynamics is a technology consulting, platform and product engineering, AI, and advanced analytics services provider. It helps enterprise companies address technical challenges and achieve business outcomes during digital transformation, with expertise in enterprise AI, data, analytics, cloud and DevOps, application modernization, and customer experience.

• Design, implement, and maintain secure, scalable AI agent infrastructure on Google Cloud Platform using Vertex AI, Agentspace, and the Agent Development Kit (ADK);
• Build, deploy, and manage custom Model Context Protocol (MCP) actions with safe, compliant, and deterministic model execution boundaries;
• Establish enterprise security and Identity Access Management frameworks, including Workload Identity Federation, short-lived tokens, RBAC, and cross-cloud alignment;
• Operationalize AI solutions through automated CI/CD pipelines, compliance checks, and Infrastructure as Code using Terraform and GitHub Actions;
• Develop event-driven workflow orchestrations and scalable data pipelines using Google Pub/Sub, Python, Elasticsearch, and BigTable;
• Implement continuous monitoring, tracing, and observability for AI agents using OpenTelemetry, Grafana, LangSmith, and PagerDuty alerting;
• Enforce policy-as-code and real-time security across Google Kubernetes Engine (GKE) and containerized environments using OPA, VPC, and private endpoints.

• 5+ Years of hands-on experience in Cloud & AI Software Engineering focused on production AI/ML systems on Google Cloud Platform;
• Proven experience building and deploying intelligent agents using Vertex AI, Agent Engine, and Google Cloud Agent Development Kit (ADK);
• Strong proficiency in Python for AI development, data processing, and API integration;
• Hands-on experience with Model Context Protocol (MCP) design, implementation, and tool execution;
• Experience with Terraform and GitHub Actions for automated, policy-driven cloud deployments;
• Practical understanding of enterprise cloud security, including Workload Identity Federation, RBAC, Open Policy Agent (OPA), VPC, and private endpoints;
• Experience with AI observability, tracing, and monitoring tools such as OpenTelemetry, Grafana, and LangSmith;
• Experience with messaging frameworks and NoSQL data stores, including Google Pub/Sub, Elasticsearch, and BigTable;
• Excellent problem-solving skills;
• Written and verbal English communication for global team collaboration;
• Nice to have: Docker, Kubernetes, Google Kubernetes Engine (GKE), cross-cloud identity federation between Azure AD and Google Workspace, PagerDuty, automated policy enforcement frameworks, retail, supply chain, or high-throughput e-commerce platforms.

• Competitive salary;
• Flexible schedule;
• Medical insurance and sports benefits;
• Corporate social events;
• Professional development opportunities;
• Well-equipped office.