LLM & Agentic AI / SRE Engineer
- Location
- Phoenix, Arizona, United States
- Salary
- Not specified
- Company
- Akash pawar
Job description
• Role & Company / Project Overview Tekgence is seeking an experienced LLM & Agentic AI / SRE Engineer for a 12+ months contract position in Phoenix, AZ. This hybrid role focuses on designing, building, and operating LLM-powered and agentic AI products while guaranteeing enterprise-grade reliability, observability, and production resilience. Local candidates only. • Key Responsibilities & Daily Duties - Design and ship LLM-powered and Agentic AI features and systems. - Build AI agents capable of reasoning, tool calling, real-world actions, and graceful failure recovery. - Integrate existing AI tools using major AI frameworks and libraries. - Own SLA, SLO, error budgets, MTTD/MTTR, and reliability reporting. - Architect observability using Elastic/Kibana, Prometheus, and Grafana. - Build advanced alerting, anomaly detection, automated routing, runbooks, and remediation workflows. - Lead 24x7 incident response, service restoration, stakeholder communication, and blameless RCA. - Design and validate Disaster Recovery, failover, RTO/RPO, and DR drills. - Drive production readiness, resiliency, performance, capacity planning, and infrastructure optimization. - Review production changes, deployments, rollback/recovery, and release validations. - Lead EMIM bridges, cross-team troubleshooting, and technical incident coordination. - Identify recurring failure patterns and drive permanent corrective/preventive actions. • Required Qualifications, Skills & Experience - Demonstrated track record in designing, building, and operating LLM-powered and agentic AI products. - Deep technical knowledge of AI frameworks, tool calling, agentic workflows, and reasoning paradigms. - Robust SRE background with proven experience in SLAs, SLOs, error budgets, and MTTD/MTTR ownership. - Extensive observability expertise using Elastic/Kibana, Prometheus, and Grafana. - Experience in 24x7 incident response, RCA, Disaster Recovery design, failover, and RTO/RPO validation. - Must be a local candidate to Phoenix, AZ. • Working Hours, Shifts & Location Details - Location: Phoenix, Arizona (AZ), United States - Work Arrangement: Hybrid - Engagement Type: 12+ months contract • Application Instructions Share your profile along with your current visa status and location directly with the recruiter.