interface.ai
At interface.ai, we are building BankGPT - the world's first AI-powered digital banking platform that leverages large language models, multi-agent orchestration, real-time streaming, and voice AI. To support this mission, we are seeking a DevOps Engineer III who will own infrastructure end-to-end, design systems from scratch, and enable highly resilient AI workloads at scale. This is a senior, hands‑on role that requires deep expertise in cloud-native DevOps, infrastructure automation, observability, and security. You'll not only build and optimize systems but also influence best practices, mentor peers, and contribute to critical decision‑making around platform reliability and scalability.
Responsibilities
Infrastructure Ownership - Design, implement, and scale infra across AWS, GCP, or Azure; drive high availability, multi‑AZ, and DR/BCP strategies.
Cloud‑Native Enablement - Build and manage Kubernetes clusters (EKS/GKE), service mesh (Istio/Linkerd), and ingress controllers for secure and resilient workloads.
CI/CD and Automation - Architect CI/CD pipelines (ArgoCD/GitOps, Jenkins) and build custom deployment portals and automation tools to accelerate developer productivity.
AI/LLM Reliability - Define and track key metrics (latency, cost, throughput, containment) for AI/LLMs and agent workflows.
Observability and Tracing - Implement end‑to‑end tracing for multi‑turn queries and real‑time pipelines using OpenTelemetry, Prometheus, and Grafana.
Vector Databases - Manage and tune vector DBs (Pinecone, Weaviate, Milvus, etc.) for high concurrency, hybrid retrieval, reranking, and resilience.
Resilience and Scaling - Design autoscaling, failover, and health‑check‑based routing strategies for workloads like WebSockets, RAG pipelines, and voice (STT/TTS).
Scripting and Tooling - Write Bash/Python/Go scripts for operational tooling, log rotation, API integrations, and rollout automation.
Collaboration - Partner with AI and engineering teams to support complex workflows, while driving DevOps best practices across the organization.
Requirements
5-8 years of core DevOps experience with a strong track record of building infrastructure from scratch (not just maintaining existing systems).
Deep expertise in Docker, Kubernetes, Helm, and container orchestration.
Hands‑on with Terraform, Crossplane, and declarative infra management.
Strong experience in CI/CD pipelines (ArgoCD, Jenkins, GitOps workflows) and building custom automation.
Proven ability to deploy AI/LLMs and agent workflows reliably in production.
Expertise in defining/tracking AI workflow metrics and observability of multi‑turn queries.
Mandatory expertise with vector databases - tuning, scaling, and optimizing retrieval performance.
Proficiency in monitoring and logging tools (Prometheus, Grafana, OpenTelemetry, ELK/OpenSearch).
Familiarity with service mesh (Istio/Linkerd), networking, and multi‑cluster workloads.
Proficiency in scripting/programming (Python, Bash, Go preferred).
Knowledge of security best practices in cloud environments (IAM, secrets, secure networking).
Bonus Points
Experience working on AI‑enabled or ML‑integrated platforms.
Understanding of compliance, security, and auditability requirements in regulated environments.
Prior experience working in a fast‑paced, high‑growth product team.
#J-18808-Ljbffr
Responsibilities
Infrastructure Ownership - Design, implement, and scale infra across AWS, GCP, or Azure; drive high availability, multi‑AZ, and DR/BCP strategies.
Cloud‑Native Enablement - Build and manage Kubernetes clusters (EKS/GKE), service mesh (Istio/Linkerd), and ingress controllers for secure and resilient workloads.
CI/CD and Automation - Architect CI/CD pipelines (ArgoCD/GitOps, Jenkins) and build custom deployment portals and automation tools to accelerate developer productivity.
AI/LLM Reliability - Define and track key metrics (latency, cost, throughput, containment) for AI/LLMs and agent workflows.
Observability and Tracing - Implement end‑to‑end tracing for multi‑turn queries and real‑time pipelines using OpenTelemetry, Prometheus, and Grafana.
Vector Databases - Manage and tune vector DBs (Pinecone, Weaviate, Milvus, etc.) for high concurrency, hybrid retrieval, reranking, and resilience.
Resilience and Scaling - Design autoscaling, failover, and health‑check‑based routing strategies for workloads like WebSockets, RAG pipelines, and voice (STT/TTS).
Scripting and Tooling - Write Bash/Python/Go scripts for operational tooling, log rotation, API integrations, and rollout automation.
Collaboration - Partner with AI and engineering teams to support complex workflows, while driving DevOps best practices across the organization.
Requirements
5-8 years of core DevOps experience with a strong track record of building infrastructure from scratch (not just maintaining existing systems).
Deep expertise in Docker, Kubernetes, Helm, and container orchestration.
Hands‑on with Terraform, Crossplane, and declarative infra management.
Strong experience in CI/CD pipelines (ArgoCD, Jenkins, GitOps workflows) and building custom automation.
Proven ability to deploy AI/LLMs and agent workflows reliably in production.
Expertise in defining/tracking AI workflow metrics and observability of multi‑turn queries.
Mandatory expertise with vector databases - tuning, scaling, and optimizing retrieval performance.
Proficiency in monitoring and logging tools (Prometheus, Grafana, OpenTelemetry, ELK/OpenSearch).
Familiarity with service mesh (Istio/Linkerd), networking, and multi‑cluster workloads.
Proficiency in scripting/programming (Python, Bash, Go preferred).
Knowledge of security best practices in cloud environments (IAM, secrets, secure networking).
Bonus Points
Experience working on AI‑enabled or ML‑integrated platforms.
Understanding of compliance, security, and auditability requirements in regulated environments.
Prior experience working in a fast‑paced, high‑growth product team.
#J-18808-Ljbffr