AI Platform Engineer

AI Platform Engineer Position Overview We are seeking an experienced AI Platform Engineer to build and operate the foundational infrastructure that powers AI-driven game development, live-service operations, player experiences, and studio-wide AI initiatives. This role focuses on creating scalable AI platforms, deployment pipelines, model serving infrastructure, monitoring systems, and developer tooling that enable game teams to efficiently build, deploy, and manage AI-powered applications. Key Responsibilities AI Platform Architecture Design, build, and maintain enterprise-scale AI platforms that support model development, deployment, monitoring, evaluation, and lifecycle management. Develop self-service infrastructure and tooling that enable game studios to rapidly deploy and manage AI-powered applications. Establish platform standards, architecture patterns, and operational best practices for AI workloads. Build scalable multi-tenant environments supporting multiple game projects and development teams. Drive continuous improvements in platform reliability, performance, security, and developer productivity. Model Deployment & Serving Infrastructure Design and implement model deployment pipelines supporting machine learning models, Large Language Models (LLMs), recommendation systems, and AI agents. Build scalable model serving infrastructure capable of supporting real-time and batch inference workloads. Develop automated deployment workflows, rollback mechanisms, and version management systems. Implement canary deployments, blue-green deployments, and progressive rollout strategies for AI services. Optimize model serving performance, latency, throughput, and resource utilization across production environments. MLOps & AI Operations Establish end-to-end MLOps workflows covering training, testing, deployment, monitoring, retraining, and governance. Develop automated CI/CD pipelines for machine learning and AI applications. Implement model registry solutions, artifact management systems, and reproducible deployment processes. Support experiment tracking, feature management, and model lifecycle automation. Collaborate with AI teams to improve development workflows and reduce time-to-production for AI solutions. Monitoring, Evaluation & Observability Design and implement comprehensive monitoring systems for AI models, inference services, and platform infrastructure. Track model accuracy, latency, throughput, drift, hallucination rates, retrieval quality, and business performance metrics. Develop evaluation frameworks for Large Language Models, retrieval systems, recommendation engines, and AI agents. Create dashboards, alerting systems, and operational analytics supporting proactive issue detection. Perform root-cause analysis and implement improvements to increase platform reliability and service quality. AI APIs & Developer Platforms Develop APIs, SDKs, and service layers that expose AI capabilities to game clients, backend systems, and studio development teams. Build reusable platform services supporting embeddings, vector search, retrieval pipelines, inference routing, and model orchestration. Create developer tools that simplify integration of AI services into game applications. Design authentication, authorization, rate limiting, and service governance mechanisms. Ensure platform APIs are scalable, secure, and easy to adopt across engineering teams. Cloud Infrastructure & Platform Engineering Build and manage cloud-native infrastructure across AWS, Google Cloud Platform (GCP), and/or Microsoft Azure. Design highly available, fault-tolerant systems supporting mission-critical AI workloads. Implement Infrastructure as Code (IaC) using Terraform and related automation tools. Manage Kubernetes clusters, container orchestration platforms, networking, and service meshes. Optimize infrastructure costs while maintaining performance and operational reliability. Security, Governance & Compliance Implement security controls protecting AI services, model assets, datasets, and infrastructure resources. Develop governance frameworks supporting responsible AI deployment and operational compliance. Establish access management, secrets management, encryption, and auditing mechanisms. Ensure platform architectures comply with organizational security policies and industry best practices. Conduct infrastructure reviews and risk assessments for AI systems operating in production. Cross-Functional Collaboration Partner with AI engineers, machine learning teams, game developers, DevOps engineers, and architects to deliver platform capabilities. Support game studios in adopting AI technologies and deploying AI-powered services. Participate in architecture reviews, technical planning sessions, and platform roadmap discussions. Mentor engineers on cloud-native development, MLOps practices, and AI infrastructure technologies. Stay current with advancements in AI platforms, cloud infrastructure, and distributed systems. Required Qualifications Bachelor's or Master's degree in Computer Science, Software Engineering, Information Systems, or a related technical discipline. Strong experience building and operating cloud-native infrastructure in production environments. Hands‑on expertise with Kubernetes, container orchestration, and distributed systems. Experience implementing Infrastructure as Code using Terraform or similar technologies. Strong understanding of Docker, containerization strategies, and cloud deployment architectures. Experience building MLOps platforms, AI infrastructure, or machine learning deployment systems. Proficiency in Python, Go, or TypeScript for infrastructure automation and platform development. Experience designing and developing APIs, microservices, and backend platform services. Knowledge of CI/CD systems, automated testing, and deployment pipelines. Experience working with AWS, Google Cloud Platform (GCP), or Microsoft Azure. Strong troubleshooting, debugging, and performance optimization skills. Excellent communication and collaboration abilities. Preferred Qualifications Experience supporting AI workloads within gaming, entertainment, or live-service environments. Familiarity with Large Language Models (LLMs), embeddings, vector databases, and Retrieval-Augmented Generation (RAG) architectures. Experience operating model serving platforms such as KServe, Ray Serve, Seldon Core, BentoML, or similar technologies. Knowledge of model evaluation, prompt testing, AI observability, and LLM monitoring frameworks. Experience with vector databases including Pinecone, Weaviate, Milvus, Qdrant, or Chroma. Familiarity with service meshes, API gateways, and distributed networking architectures. Experience implementing platform security, compliance, and governance controls. Knowledge of event‑driven architectures, streaming platforms, and real‑time processing systems. Experience building internal developer platforms and self‑service infrastructure solutions. Background in DevOps, Site Reliability Engineering (SRE), or platform engineering organizations. Technical Environment Programming Languages: Python, Go, TypeScript, Bash Infrastructure & Containers: Kubernetes, Docker, Helm, Container Registries Infrastructure as Code: Terraform, Pulumi, CloudFormation Cloud Platforms: AWS, Google Cloud Platform (GCP), Microsoft Azure MLOps Platforms: MLflow, Kubeflow, KServe, Ray Serve, Seldon Core, BentoML AI Technologies: OpenAI, Anthropic, Gemini, Llama, Embeddings, Vector Search Vector Databases: Pinecone, Weaviate, Milvus, Qdrant, Chroma CI/CD & Automation: GitHub Actions, GitLab CI, Jenkins, ArgoCD Observability: Prometheus, Grafana, Datadog, OpenTelemetry, ELK Stack Backend Technologies: FastAPI, Flask, Node.js, gRPC, REST APIs Security & Governance: IAM, Vault, Secrets Management, Encryption, Audit Logging What Success Looks Like AI deployment pipelines enable rapid and reliable model releases across multiple game studios. Platform infrastructure supports highly available, scalable, and cost-efficient AI workloads. Monitoring and evaluation systems provide comprehensive visibility into model quality, performance, and business impact. Developers can easily integrate AI capabilities through standardized APIs and platform services. MLOps processes reduce operational overhead while accelerating AI innovation. AI services maintain strong reliability, security, and performance under production workloads. Game studios successfully leverage the platform to build and deploy AI‑powered experiences faster and more effectively. #J-18808-Ljbffr