DevOps Engineer

!! Hiring !! Job Title: Senior DevOps Engineer – AI Infrastructure (GCP )Location : Pune Hybri dExperience : 5+ Year sNotice- Immediate to 30 Day s About the Ro leWe are looking for a highly skille d Senior DevOps Engine er with strong expertise i n Google Cloud Platform (GCP), Kubernetes, Infrastructure as Code, and AI/LLMO ps. The ideal candidate will own production infrastructure, build scalable AI deployment pipelines, optimize cloud infrastructure, and ensure high availability, security, and observability of AI-powered application s.This role requires hands-on experience with modern cloud-native technologies, CI/CD automation, container orchestration, and AI infrastructure supporting Large Language Models (LLMs ).Key Responsibiliti esInfrastructure & Production Operation s.Build comprehensive monitoring and alerting for production service s.Troubleshoot, diagnose, and resolve production incidents with minimal downtim e.Continuously improve system reliability, scalability, and performanc e.Infrastructure as Code (Ia C)Design, deploy, and maintain scalable cloud infrastructure using Terraform and Ansibl e.Automate provisioning and configuration management across environment s.Maintain reusable, secure, and version-controlled infrastructure template s.AI Infrastructure & LLMO psDesign and manage deployment pipelines for AI applications and LLM-powered service s.Deploy and maintain vector databases such as Pinecone, Weaviate, Elasticsearch, or Vertex AI Searc h.Manage AI model endpoints and optimize API rate limiting, throttling, and inference performanc e.Support AI infrastructure on Vertex AI and related GCP AI service s.DevSecOps & Securi tyImplement security-by-design principles across infrastructur e.Manage IAM policies using least-privilege acces s.Implement Secret Manager and secure credential managemen t.Automate vulnerability scanning for containers, infrastructure, and AI workload s.Ensure compliance with cloud security best practice s.CI/CD & Automati onDesign and maintain secure CI/CD pipelines for microservices and AI workload s.Automate deployment, testing, and configuration managemen t.Build pipelines for AI models, prompts, and configuration managemen t.Improve deployment speed while maintaining reliability and securit y.Observability & Monitori ngImplement centralized monitoring and loggin g.Track AI-specific metrics includin g:Token consumpti onInference laten cyModel error rat esAPI usa geInfrastructure performan ceBuild dashboards and proactive alerting mechanism s.Cloud Governance & Cost Optimizati onOptimize GCP infrastructure cost s.Manage GPU/TPU resource utilizatio n.Monitor quotas and recommend cost-saving strategie s.Ensure efficient resource allocation across environment s.Multi-Cloud Infrastructu reDesign and optimize secure connectivity between AWS and GCP environment s.Support hybrid and multi-cloud deployment s.Ensure seamless communication between distributed application s.Required Skills & Qualificatio ns5+ years of experience in DevOps, Cloud Infrastructure, or Site Reliability Engineerin g.Expert-level experience with Google Cloud Platform (GCP), includin g:G KECloud R unVertex AIGoogle Cloud Storage (GC S)Network Endpoint Groups (NE G)Strong experience with Kubernetes and Docke r.Hands-on experience with Terraform and Ansibl e.Experience deploying and managing vector databases such a s:Pineco neWeavia teElasticsear chVertex AI Sear chExperience monitoring AI workloads and LLM metric s.Strong knowledge of Ubuntu/Linux administratio n.Expertise in networking, IAM, cloud security, and infrastructure hardenin g.Proficiency in Python and Bash scriptin g.Experience building scalable, fault-tolerant, and highly available cloud architecture s.Strong debugging and performance optimization skill s.Experience automating operational tasks and infrastructure managemen t.Excellent communication, collaboration, and documentation skill s.Ability to mentor junior engineers and work effectively in cross-functional team s.Preferred Qualificatio nsExperience with LLMOps and Generative AI platform s.Hands-on experience with Vertex AI ecosyste m.Familiarity with GPU/TPU resource optimizatio n.Experience implementing GitOps workflow s.Knowledge of AI inference optimization and model deployment strategie s.Exposure to SRE practices, incident response, and disaster recovery plannin g. If you will be interested please share your candidat [email protected] bal