Senior AI Platform Engineer

Skills

• Strong cloud engineering and AI/ML platform engineering experience
• Kubernetes, containers, Infrastructure as Code, CI/CD, and API technologies
• Python and software engineering experience
• Experience with ML/LLM deployment and GenAI frameworks
• Knowledge of vector databases, embedding models, model APIs, and AI orchestration
• Experience with monitoring, telemetry, security, and production support
• Programming: Advanced proficiency in Python; additional experience in Go, C++, or Rust is often preferred
• Infrastructure & Cloud: Hands-on expertise with Kubernetes, Docker, and cloud platforms like AWS (SageMaker, Bedrock) or Azure (AI Foundry, OpenAI)
• AI Frameworks: Familiarity with orchestration and LLM tooling such as LangChain, LangGraph, Ray, or Kubeflow
• Infrastructure-as-Code (IaC): Knowledge of automation tools like Terraform and Ansible

Responsibilities

• Build and maintain enterprise AI/ML and GenAI platform capabilities
• Implement model endpoints, gateways, orchestration layers, and AI services
• Build infrastructure supporting LLMs, SLMs, RAG, embeddings, vector stores, and AI agents
• Develop automated deployment and CI/CD pipelines for AI applications and models
• Implement LLMOps/MLOps capabilities covering deployment, monitoring, evaluation, versioning, and observability
• Implement model-routing and inference-management capabilities
• Support token, compute, latency, and inference-cost optimization
• Integrate AI platforms with enterprise identity, security, logging, monitoring, networking, and API-management services
• Automate infrastructure provisioning and platform configuration
• Establish production reliability, scalability, resilience, and operational standards
• Partner with AI architects, application engineers, data engineers, and security teams
• Platform Architecture: Design and deploy scalable, cloud-native or bare-metal infrastructure (using Kubernetes, OpenShift, or AWS/Azure) to support large language models (LLMs) and machine learning workloads
• Model Operations (MLOps/LLMOps): Optimize model serving, inference performance, GPU utilization, and automated pipelines for fine-tuning and deploying AI models
• Agentic & GenAI Integration: Build and maintain shared services like AI gateways, Retrieval-Augmented Generation (RAG) frameworks, and autonomous agent orchestration platforms
• Governance & Security: Enforce enterprise data protection, compliance, auditability, and cybersecurity standards across all AI tooling
• Developer En