Senior DevOps Engineer for Voice AI and AI Infrastructure

We are looking for a highly capable DevOps or Platform Engineer based in Latin America to help us manage, scale, and improve the infrastructure behind our production Voice AI platform. This is not a traditional CI/CD-focused DevOps role. We need someone with strong experience in cloud infrastructure, Kubernetes, real-time systems, networking, observability, and AI workloads. Our platform handles real-time voice conversations and includes components such as SIP servers, LiveKit, Asterisk, WebSockets, AI model services, GPU infrastructure, Kubernetes, and cloud-native services. Responsibilities Review and improve our existing cloud and Kubernetes architecture Manage production deployments across AWS and Azure Improve reliability, scalability, and fault tolerance Troubleshoot SIP, RTP, WebSocket, networking, and real-time media issues Support Asterisk and LiveKit-based voice infrastructure Set up and improve monitoring, alerting, logging, and incident response Optimize infrastructure for high-concurrency voice workloads Manage GPU-based AI inference workloads Improve autoscaling, resource allocation, and cost efficiency Review security, networking, secrets management, and access controls Investigate production incidents and perform root-cause analysis Automate deployments using Terraform, Helm, GitHub Actions, or similar tools Work closely with our AI, backend, and voice engineering teams Required Experience Strong hands-on experience with Kubernetes, Docker, Helm, and Linux Strong experience with AWS, Azure, or both Experience with Terraform or other infrastructure-as-code tools Experience with Prometheus, Grafana, Loki, OpenTelemetry, or similar tools Strong understanding of networking, load balancing, DNS, TLS, and firewalls Experience managing production systems with high concurrency Strong troubleshooting and root-cause analysis skills Experience with Python, Bash, Go, or another scripting language Good written and spoken English High availability and fast communication during critical incidents Strongly Preferred Experience with Voice AI, conversational AI, or real-time communication platforms Experience with LiveKit, Asterisk, Kamailio, OpenSIPS, FreeSWITCH, or similar systems Understanding of SIP, RTP, WebRTC, STUN, TURN, and WebSockets Experience with GPU workloads, NVIDIA container runtime, and AI inference services Experience scaling LLM, STT, TTS, or machine-learning infrastructure Experience working with distributed systems and low-latency applications Familiarity with Redis, PostgreSQL, Kafka, NATS, or similar technologies Experience with on-premise or private-cloud deployments Engagement Freelance or long-term contract Initially milestone-based Potential for an ongoing engagement Preference for candidates based in Mexico, Colombia, Argentina, Brazil, Chile, or other LATAM countries Must overlap with US working hours Must be responsive and available during agreed production support windows Application Requirements Please include: Your location and time zone Your availability per week Your hourly or monthly rate Examples of production infrastructure you have managed Your experience with Kubernetes and high-concurrency systems Any experience with SIP, WebRTC, LiveKit, Asterisk, Voice AI, or AI infrastructure A brief description of the most difficult production incident you have resolved Whether you are open to completing a paid technical assessment Please do not apply if your experience is primarily limited to basic CI/CD pipelines, website hosting, or standard application deployments. We are looking for someone who can independently investigate complex production infrastructure and real-time communication issues.