Agentic AI Engineer (Cloud & DevOps)

Job Description

AI platform development to improve DevOps and Infra workflows. Software design, interface design, micro service development, java back-end development, workflow development and testing. Develops AI prompts and other strategies to improve the consistency, relevance and accuracy of LLM workflows and Agentic AI experiences. Works with Team Leads, applications architects and QA testers. Deliver quality code with proper documentation that meet the needs of the business. Helps drive Agentic AI adoption within the EngOps team.

Roles & Responsibilities:

1. Support new cloud solutions through use and development of AI Agents - involves UAT, ORT testing and driving operational requirements. Outputs include Infrastructure as Code, Test Plans, Test Cases, Test Execution, Production Verification, Developer and Administrative Portals.
2. Maintain overall platform stability/security/ supportability. Interface with development teams, vendors, product, sales and customers to design and implement AI solutions that streamline maintenance and sustainment activities. Engineer operational requirements, test cases, technical documentation provide operational support.
3. Monitor, maintain, & support cloud solutions. Ensure standard processes exist for systems installation, configuration, patching, and upgrading through CI/CD pipelines, automation, and AI Agent recommendations development for these areas.
4. Develop guidelines for systems monitoring for maximum availability, uptime, and performance. Research, troubleshoot, resolve system issues/outages. Enhance monitoring and alerting, reduce mean time to restore, and develop proactive monitoring solutions that enable AI Agents to identify issues and recommend remediation.
5. Support of web portals, orchestration, platform, application, API, network and monitoring needs. Platform support (monitoring capabilities, performance tuning, capacity planning, and maintaining overall service and platform health) through automation and AI Agent implementation.
6. Facilitate post-outage reviews (POR), manage Service Incident Reporting (SIR), develop and deliver Root Cause Analysis (RCA) to management and to the customer.

Top 5 Skills Required

1. Agentic AI Frameworks & MCP - Deep understanding of agentic AI architectures and frameworks such as LangGraph, LangChain, CrewAI, AutoGen, and Model Context Protocol (MCP). Experience designing AI agents that can reason, retrieve contextual information, orchestrate workflows, interact with enterprise tools, and automate infrastructure and operational processes.
2. AI Evaluation, Observability & Problem Solving - Demonstrated expertise in AI system evaluation, prompt and context engineering, observability, performance monitoring, and operational troubleshooting. Ability to assess agent effectiveness, improve accuracy and reliability, identify failure patterns, perform root cause analysis, and develop AI-driven recommendations that enhance platform stability and operational resilience.
3. Python & API Integration Development - Strong software engineering skills with emphasis on Python development, API integration, microservices, and automation frameworks. Experience developing AI-powered services that integrate with cloud platforms, DevOps toolchains, monitoring systems, CMDBs, ticketing platforms, and enterprise data sources to enable intelligent automation and decision-making.
4. Cloud / Infrastructure Engineering - Expertise in cloud and infrastructure technologies, including Kubernetes, Azure, AWS, networking, security, observability, and platform operations. Ability to translate infrastructure requirements into scalable AI-driven automation solutions that improve deployment, monitoring, reliability, and operational efficiency.
5. Infrastructure as Code (IaC) & GitOps - Hands-on experience with Infrastructure as Code and GitOps practices using technologies such as Terraform, Bicep, Helm, ArgoCD, and CI/CD platforms. Proven ability to automate infrastructure provisioning, environment buildouts, configuration management, deployment pipelines, and release validation workflows.

Qualifications/Experience

• 3 to 5 years of experience (or more)
• If only Agentic Systems - can be hands-on Agentic framework related experience so ~ 1 year or more

Education

• A Bachelor's or Master's degree in Computer Science or Engineering Degree , AI, Engineering, or a related field is typically required. A PhD may be a plus for senior roles.

Certifications

• AI related
• Cloud – Azure or AWS (Optional)
• Javascript and associated frameworks (Optional, but preferable)
• Data Analytics, Modeling, or Science (Optional, but experience a plus)

Soft-Skills

• Problem-solving - with strong analytical skills (should be able to tackle complex issue and AI hurdles
• Adaptability - proactive and a good mindset in a fast-paced AI world
• Strong communication skills - should be able to also deep dive into technical AI insights (not just non-technical communications)
• Collaboration - Experience working as a team and as an independent contributor
• Ethical AI - secure deployments, responsible and ethical AI practices

Technical Skills

• Typescript, Nest.js (and how they can be used for AI / Agentic AI)
• Python (and how it can be used for AI Work)
• AI/ML Concepts - Knowledge and implementation experience. Deep understanding of prompts, strategies, RAG.
• GenAI, AI, LLMs - Knowledge and implementation experience
• Agentic Frameworks - Knowledge and implementation experience. Deep understanding of Context Engineering, LangChain, LangGraph, CrewAI, AutoGen, Web Scraping Tools. Understanding of MCPs, Agentic RAG (Supabase, Vectorize, Pinecone, Weaviate are all a plus), Evals, Tools etc.
• Programming - strong programming skills in Python, Typescript, Nest.js, Go, Java
• Software and Systems Engineering - APIs, REST APIS, understanding. CI/CD, Docker, K8s, Cloud understanding is critical
• Experience with Claude Code, Cursor, Lovable are a huge plus
• Knowledge and working experience with Figma, Windsurf, Replit, or Visual Studio Code are a must have.