Agentic AI Engineer

We are looking for an Agentic Automation Engineer to design, develop, and scale intelligent AI agents that automate complex business processes across the organization. This role combines expertise in AI, software engineering, and automation to build production-ready agentic solutions using Google Cloud AI technologies, modern LLM frameworks, and enterprise automation platforms. You will be responsible for the complete lifecycle of AI agents - from architecture and implementation to deployment, monitoring, governance, and continuous improvement—while establishing engineering standards and reusable components for the wider team.

• Design and implement enterprise-grade AI agents capable of reasoning, planning, decision-making, and autonomous task execution.
• Develop multi-agent systems where specialized agents collaborate, exchange information, delegate tasks, and validate each other’s outputs.
• Build scalable agent architectures using Agent Development Kit (ADK), Google Cloud Vertex AI, Gemini models, Agent Engine, and related Google AI services.
• Integrate AI agents with enterprise applications, APIs, databases, RPA platforms, and internal business systems.
• Design Retrieval-Augmented Generation (RAG) solutions using vector databases, semantic search, embeddings, and knowledge repositories.
• Implement context management strategies including conversational memory, long-term memory, retrieval mechanisms, and context optimization.
• Develop secure agent workflows with authentication, authorization, encryption, audit logging, and enterprise governance controls.
• Build tool integrations using REST APIs, MCP-compatible tools, databases, messaging platforms, and external services.
• Develop Python-based services, utilities, and integrations supporting AI agent capabilities.
• Monitor, evaluate, and optimize AI agents for quality, latency, cost efficiency, reliability, and business impact.
• Create reusable agent templates, architectural patterns, shared components, and technical documentation.
• Collaborate with business stakeholders to identify automation opportunities and translate them into intelligent agent solutions.
• Mentor engineers and promote best practices in Agentic AI, LLM engineering, and intelligent automation.
   

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, Artificial Intelligence, or a related technical field.
• 1+ years of experience in software engineering, intelligent automation, or AI solution development.
• Hands-on experience building applications powered by Large Language Models (LLMs).
• Experience with Google Cloud Platform, particularly Vertex AI and Gemini models.
• Experience designing AI agents, agent workflows, or multi-agent systems.
• Solid knowledge of Python for backend development and AI integrations.
• Experience with Retrieval-Augmented Generation (RAG), embeddings, vector databases, and semantic search.
• Experience integrating AI solutions with REST APIs, enterprise systems, databases, and cloud services.
• Understanding of prompt engineering, evaluation methodologies, context management, and memory strategies.
• Knowledge of authentication, OAuth, API security, and enterprise security principles.
• Familiarity with Git, CI/CD pipelines, Docker, and cloud-native deployment practices.
• Experience implementing monitoring, logging, tracing, and performance optimization for AI applications.
• Strong analytical and problem-solving skills.
• English proficiency at B2 level or higher.

Preferred Qualifications

• Experience with Google Agent Development Kit (ADK), Agent Engine, and Google Cloud Agentic AI architecture.
• Google Cloud certifications such as Cloud Digital Leader (https://cloud.google.com/certification/cloud-digital-leader), Generative AI Leader, or Cloud Developer.
• Experience with enterprise automation platforms such as UiPath.
• Knowledge of Model Context Protocol (MCP) and tool orchestration concepts.
• Experience deploying AI solutions in regulated industries such as banking, finance, or insurance.
• Understanding of Responsible AI principles, model governance, and AI risk management.