**Role Summary**:Own the operational lifecycle of LLM-powered systems including prompt versioning, model configuration, cost controls, and production reliability across Snowflake-native and API-based GenAI platforms.
**The Core Challenge**:This role bridges that gap by providing **standardized infrastructure, deployment pipelines, and operational frameworks** so AI teams can move fast without sacrificing reliability, security, or governance.
**Key Responsibilities**:**GenAI Platform & Infrastructure**:- Support Snowflake-based AI workflows including **data ingestion, Cortex Agents, Analyst, and Search**:- Implement cost-aware infrastructure patterns (warehouse sizing, service isolation, token budgeting) for GenAI workloads- Explore, build, and support proof-of-concept initiatives to evaluate emerging GenAI and MLOps platforms and architectures, focusing on deployment, orchestration, monitoring, and governance of LLM-based systems.
**CI/CD & Automation**:- Automate infrastructure provisioning and environment configuration using Infrastructure-as-Code- Enable safe, repeatable deployments with versioning, rollback, and environment promotion strategies**Observability & Reliability**:- Implement observability for GenAI systems using **Langfuse and Snowflake observability tools**to continuously improve AI system reliability and usefulness.
**Cloud & Container Operations**:- Manage containerized workloads across **GCP and Snowflake containers**:- Ensure secure networking, secrets management, access controls, and environment isolation**Enterprise Integrations**:- Ensure reliability, security, and observability of API-based and event-driven integrations**Collaboration & Enablement**:- Partner closely with AI engineers, data engineers, and IT teams to remove operational blockers- Provide documentation, templates,



and best practices that enable teams to deploy and operate independently- Contribute to standards for security, reliability, and governance across the GenAI platform**Required Qualifications**:- 3+ years in DevOps, platform engineering, or software infrastructure roles; 1-2+ years specifically with ML/AI infrastructure or MLOps- Strong experience with **CI/CD pipelines** (GitHub Actions preferred)- Experience operating workloads on **GCP** or similar cloud platforms- Proficiency with **Infrastructure-as-Code** tools (Terraform or equivalent)- Strong scripting skills (Python and/or Bash)- Experience implementing **monitoring, logging, and observability** for production systems- Ability to troubleshoot and operate complex distributed systems- Strong communication skills and ability to collaborate across technical and business teams- Fluent in English (written and spoken)- Bachelor's or Master's degree in Computer Science, Software Engineering, IT, or related field (or equivalent experience)**Preferred Qualifications**:- Experience with **Langfuse or similar AI observability tools**:- Experience integrating enterprise systems (SAP, Salesforce, SharePoint, etc.)- Experience with data versioning tools (DVC, Pachyderm, LakeFS)- Knowledge of vector databases and LLM infrastructure (Pinecone, Weaviate, Milvus, Chroma)- Cloud or MLOps certifications (AWS Machine Learning Specialty, AWS Solutions Architect, Kubernetes CKA/CKAD, Azure AI Engineer, GCP ML Engineer)- Manufacturing or industrial IoT experience- Experience with compliance and governance frameworks for AI/ML systems**_What This Role IS_**- Infrastructure engineer who enables AI teams to move faster through automation and robust tooling- Systems thinker who balances reliability, scalability, and cost efficiency- Bridge between AI innovation and production operations who translates complex requirements into practical solutions- Continuous learner who keeps current with rapidly evolving AI-Ops ecosystem and cloud-native technologies

📌 Ai Devops Engineer (Xico)
🏢 Ingersoll Rand
📍 Xico