Agentic AI DevOps Specialist
AI Summary
An Agentic AI DevOps Specialist designs, deploys, and operates an enterprise-grade Agentic AI Platform, building and maintaining Kubernetes-based infrastructure, IaC, and CI/CD pipelines while enabling self-service developer workflows.
About this role
π Join Our Data Products and Machine Learning Development Remote Startup! π
We are looking for an Agentic AI DevOps Specialist to join a strategic initiative focused on building, deploying, and operating an enterprise-grade Agentic AI Platform. This platform will enable developers across the organization to self-service infrastructure, AI capabilities, prompts, and reusable agentic components through standardized, governed, and scalable development paths.
You will work closely with the Technical Lead, contributing hands-on expertise in both DevOps and Agentic AI technologies while helping drive the platform's long-term sustainability and adoption.
π What We Do
π Our Partnerships
π Our Values
Responsibilities π€
Required Skills π»
DevOps & Platform Engineering
- 4+ years of experience in DevOps, Platform Engineering, SRE, or Backend Engineering.
- Strong Kubernetes experience, including administration, networking, Helm, and automation.
- Experience with Terraform and Infrastructure as Code.
- Experience designing and maintaining CI/CD pipelines (GitHub Actions or similar).
- Knowledge of Linux administration, containers, registries, IAM, and RBAC.
- Experience with observability, monitoring, and cloud-native infrastructure.
- Familiarity with Internal Developer Platforms (IDPs) and self-service infrastructure concepts.
-
- 1β2+ years of hands-on experience working with Agentic AI, GenAI, or LLM-based platforms.
- Experience with frameworks such as LangChain, LangGraph, LangFuse, LangSmith, or similar.
- Knowledge of prompt engineering, prompt versioning, evaluation, and A/B testing.
- Experience with RAG architectures, vector databases, embeddings, and semantic search.
- Understanding of agent orchestration patterns, autonomous agents, and tool integrations.
- Familiarity with MCP, memory layers, guardrails, and AI observability practices.
- Understanding of commercial and open-source LLMs and their trade-offs.
