Teams at Ciklum

Design and build production agentic AI systems for enterprise clients. Develop autonomous agents using Glean, OpenAI/GPT Enterprise, and AWS or GCP. Own agent lifecycles from architecture and implementation through deployment, monitoring, evaluation, and iteration. Apply tool calling, RAG, multi-step orchestration, memory, prompt engineering, structured outputs, permission-aware retrieval, and observability to create reliable, secure, maintainable enterprise-scale AI solutions.

Design, build, and operate highly available Azure and AKS infrastructure using Terraform. Develop secure CI/CD pipelines, manage Kubernetes clusters, implement monitoring and observability, troubleshoot complex infrastructure issues, and maintain multi-region disaster recovery. The role also involves cloud security, secrets management, networking, database resilience, infrastructure automation, and collaboration with application engineering teams to establish operational standards.

Administer and optimize Databricks environments on AWS across development, testing, and production. Responsibilities include workspace provisioning, Unity Catalog governance, access management, cluster and cost optimization, CI/CD, monitoring, troubleshooting, Terraform automation, security controls, compliance, and workflow orchestration. The role partners with engineering, infrastructure, InfoSec, and compliance teams to maintain secure, scalable, reliable enterprise data platforms.