Real-Time Inference

The Real-Time Inference Engineering Lead is responsible for designing, building, and operationalizing scalable, low-latency model serving platforms that power real-time AI and predictive decisioning use cases. This role leads the architecture, deployment, performance optimization, resiliency, and operational governance of online inference services across cloud and on-premises environments. Design and implement highly available, low-latency model serving architectures for real-time inference workloads. Develop and standardize deployment patterns for scalable AI/ML services across Kubernetes-based platforms. Lead API-based inference service design, integration, and lifecycle management. Optimize model serving performance through latency tuning, caching strategies, autoscaling, and resource management. Establish monitoring, observability, SLOs/SLAs, alerting, and operational runbooks for production services. Drive load testing, capacity planning, resiliency engineering, and disaster recovery readiness. Integrate inference platforms with CI/CD pipelines to enable automated deployments and controlled releases. Partner with Data Science, Platform Engineering, MLOps, and Infrastructure teams to ensure reliable production model operations. Govern operational best practices, security, reliability, and performance standards for enterprise AI deployments. Online inference and model-serving architectures Real-time APIs and distributed systems design Kubernetes, container orchestration, and service mesh technologies Autoscaling, capacity management, and workload optimization Performance engineering, load testing, and latency optimization Monitoring, observability, logging, tracing, and SLO management CI/CD, DevOps, and Infrastructure-as-Code practices Reliability engineering, fault tolerance, and resiliency patterns Cloud and on-premises platform operations Python, Java, Go, or similar backend development experience Experience with MLOps platforms and enterprise AI deployment frameworks. Hands-on experience with real-time recommendation, fraud, risk, personalization, or predictive analytics platforms. Familiarity with GPU-based inference, model optimization, and multi-cloud deployments. A successful candidate combines AI platform engineering, distributed systems expertise, and operational excellence to deliver resilient, high-performance inference platforms that enable enterprise-scale real-time AI solutions.