Job Title

Education & Experience BS in Computer Science or equivalent practical experience. 6-9 years of experience building and operating distributed systems. Proven experience delivering cloud-native platforms used in production. Core Technical Skills Strong proficiency in Python and shell scripting. Hands-on experience with Kubernetes and container orchestration. Experience building distributed systems with high availability requirements. Strong Linux, networking, and system troubleshooting skills. AI Platform Knowledge Experience supporting model training and serving pipelines. Understanding of LLM, ASR, and TTS serving patterns. Experience with prompt engineering and prompt lifecycle management. Familiarity with vector databases and retrieval-based AI systems. Ability to evaluate AI system performance from a platform perspective. Preferred Qualifications MS in Computer Science or related field. Production experience on OCI, AWS, or Azure. Experience with LLM serving frameworks (KServe, Triton, Kubeflow, . Experience with model optimization technologies (DeepSpeed, FasterTransformer). Familiarity with deep learning frameworks (PyTorch, TensorFlow, JAX). Experience building conversational voice AI systems (ASR, TTS, NLP). Exposure to AIOps or AI-driven observability solutions. IC4 Scope Clarification Owns design and implementation of AI infrastructure systems. Leads technical initiatives without people management responsibility. Influences architecture within a defined platform area. Bridges applied science and production engineering. AI Infrastructure & Automation Design and build automation frameworks for AI model training, deployment, and lifecycle management. Own and evolve model serving platforms to ensure high availability, scalability, and performance. Develop tooling for zero-touch deployments, rollbacks, and upgrades of AI services. Build self-service APIs and workflows for applied scientists and application teams. AI Serving & Platform Engineering Engineer high-performance model serving systems for LLMs, ASR, TTS, and conversational AI workloads. Optimize inference latency, throughput, and resource utilization. Partner with applied scientists to productionize models safely and efficiently. Support multi-model and multi-tenant serving architectures. Cloud-Native Software Development Design and implement backend services in Python (primary), Java or Go. Build REST and event-driven services that integrate AI platforms with contact center systems. Write production-quality code with strong testing, observability, and CI/CD integration. Reliability, Observability & Operations Define and implement observability standards (metrics, logs, traces) for AI services. Lead troubleshooting efforts for training and serving failures. Drive incident postmortems and ensure durable, automated fixes. Apply SLOs, SLIs, and error budgets to AI platforms. Technical Leadership Own end-to-end delivery of complex AI infrastructure initiatives. Mentor IC3 engineers and influence best practices. Review designs and code to ensure scalability, security, and maintainability. Act as a technical escalation point within the AI infrastructure domain. Career Level - IC4