Job Summary
We are seeking an experienced AI Engineer specializing in Google Agent Development Kit (ADK) and Agentic AI to design, develop, and deploy scalable, production-grade AI agents and multi-agent systems. The ideal candidate will have strong Python software engineering expertise, hands-on experience with Large Language Models (LLMs), and proven capabilities in agent orchestration, tool integration, multi-agent coordination, and cloud-native AI application development. This position focuses on building intelligent AI applications that integrate seamlessly with enterprise data platforms, business applications, and backend services. The engineer will be responsible for the complete AI development lifecycle, from solution architecture and rapid prototyping through production deployment, performance optimization, monitoring, and continuous improvement.
The successful candidate must have practical experience delivering reliable, secure, and observable AI agents in enterprise environments.
Key Responsibilities
1. Agentic AI Development & Multi-Agent Architecture
- Design, develop, and deploy AI agents and multi-agent workflows using Google Agent Development Kit (ADK).
- Implement advanced agent orchestration patterns, including tool calling, function execution, sub-agent delegation, and multi-agent collaboration.
- Develop agent planning, reasoning, session management, memory, and state-management capabilities.
- Design reusable agent components, frameworks, and orchestration workflows.
- Integrate AI agents with external tools, enterprise platforms, and business applications.
- Implement appropriate guardrails, access controls, and operational safeguards to ensure predictable agent behavior.
2. LLM Integration & Generative AI Engineering
- Develop AI-powered applications using Large Language Models, including Google Gemini, Anthropic Claude, OpenAI models, or comparable platforms.
- Design and optimize prompts, tool schemas, structured outputs, and model interaction workflows.
- Implement LLM API integrations and manage model configurations across different AI platforms.
- Evaluate and optimize model performance, response quality, latency, token usage, and operational costs.
- Develop evaluation methodologies to measure agent accuracy, reliability, task completion, and overall effectiveness.
- Implement automated testing, feedback loops, and continuous improvement mechanisms for AI agents.
3. Enterprise Data & Application Integration
- Integrate AI agents with enterprise data platforms such as Snowflake, Salesforce, and other business systems.
- Develop secure and reliable REST API integrations between agents, backend services, and enterprise applications.
- Collaborate with data engineering teams to expose governed, accurate, and accessible enterprise datasets.
- Implement structured data retrieval, transformation, and contextual information processing for agent workflows.
- Support SQL-based data access and integration with relational and cloud-based data platforms.
- Ensure data security, authorization, privacy, and governance requirements are maintained across AI integrations.
4. Google Cloud Platform & Production Deployment
- Develop and deploy AI applications using Google Cloud Platform (GCP).
- Utilize Vertex AI, Vertex AI Agent Engine, Cloud Run, Identity and Access Management (IAM), and Google Cloud Secret Manager.
- Implement scalable cloud-native deployment architectures for agent-based applications.
- Establish monitoring, logging, observability, and troubleshooting mechanisms for production AI services.
- Optimize cloud resource utilization, model inference performance, and application scalability.
- Implement secure credential management, environment configuration, and deployment automation.
- Support CI/CD processes, version control, automated testing, and production release management.
5. AI Agent Evaluation, Reliability & Governance
- Build evaluation frameworks to assess agent reasoning, tool usage, response quality, and task completion.
- Implement automated regression testing and validation for agent workflows.
- Develop guardrails to mitigate hallucinations, unauthorized actions, tool misuse, and unreliable outputs.
- Monitor production performance, error rates, response latency, and model consumption costs.
- Implement traceability, audit logging, and operational observability across agent interactions.
- Continuously refine agent workflows to improve accuracy, efficiency, reliability, and business outcomes.
6. Technical Collaboration & Engineering Best Practices
- Collaborate with AI engineers, software developers, data engineers, and cloud platform teams.
- Translate business and operational requirements into scalable technical architectures.
- Participate in architecture reviews, technical design discussions, code reviews, and solution optimization.
- Produce clear technical documentation covering agent architecture, integrations, APIs, deployment, and operational procedures.
- Troubleshoot complex technical issues across AI models, application services, data platforms, and cloud infrastructure.
- Communicate AI architecture, system behavior, limitations, and technical recommendations to technical and nontechnical stakeholders.
Required Qualifications
- Bachelor's degree in Computer Science, Software Engineering, Artificial Intelligence, Information Technology, or a related technical discipline, or equivalent professional experience.
- 8+ years of professional software engineering experience, including 3+ years in AI engineering or applied AI development.
- Strong hands-on experience developing AI agents using Google Agent Development Kit (ADK) or comparable frameworks such as LangGraph, AutoGen, or CrewAI, with the ability to quickly adopt ADK.
- Advanced proficiency in Python, including backend application development and API integrations.
- Demonstrated experience developing applications using LLM APIs such as Gemini, Claude, OpenAI, or equivalent models.
- Strong understanding of agentic AI architecture, including planning, tool orchestration, function calling, memory management, session state, and multi-agent coordination.
- Experience developing and integrating RESTful APIs and backend services.
- Working knowledge of Google Cloud Platform, including Vertex AI, Cloud Run, IAM, and Secret Manager.
- Proven experience deploying AI-powered applications or AI features into production environments.
- Familiarity with AI agent testing, performance monitoring, debugging, and optimization.
- Strong understanding of software engineering principles, system architecture, security, and scalable application design.
- Ability to work independently, solve complex technical challenges, and deliver solutions in rapidly evolving environments.
- Excellent analytical, problem-solving, verbal, and written communication skills.
- U.S. Citizenship is mandatory.
Preferred Qualifications
- Hands-on experience with Model Context Protocol (MCP) and agent-to-tool integration standards.
- Strong SQL skills, including Common Table Expressions (CTEs), Views, and complex query development.
- Experience with Snowflake, including Dynamic Tables, Cortex, and Cortex Analyst.
- Familiarity with Salesforce data models, Account IDs, object relationships, and enterprise CRM integrations.
- Experience developing evaluation frameworks for LLM and AI agent quality, reliability, and performance.
- Knowledge of TypeScript, JavaScript, React, Next.js, Node.js, or NestJS.
- Experience integrating AI agents into existing enterprise applications and backend architectures.
- Understanding of CI/CD, DevOps, cloud security, and production observability.
- Experience designing secure AI workflows with role-based access, human-in-the-loop controls, and enterprise governance.
- Familiarity with scalable agent orchestration, distributed systems, and production AI application architectures.
Core Technical Skills
Programming: Python, REST APIs, Backend Development, TypeScript, JavaScript
Agentic AI: Google ADK, AI Agents, Multi-Agent Systems, Agent Orchestration, Tool Calling, Function Calling, Agent Memory, State Management
AI Frameworks: LangGraph, AutoGen, CrewAI, Model Context Protocol (MCP)
Generative AI: LLMs, Gemini, Claude, OpenAI, Prompt Engineering, LLM APIs, Structured Outputs
Cloud Platform: Google Cloud Platform, Vertex AI, Vertex AI Agent Engine, Cloud Run, IAM, Secret Manager
Data Platforms: Snowflake, Snowflake Cortex, Cortex Analyst, SQL, Salesforce
Application Technologies: React, Next.js, Node.js, NestJS
Engineering Practices: CI/CD, Git, Automated Testing, Agent Evaluation, Observability, Monitoring, Security, API Integration
Expected Outcomes
The successful candidate will deliver:
- Reliable, scalable, and production-ready AI agents and multi-agent solutions.
- Secure integration of AI agents with enterprise applications, APIs, and data platforms.
- Efficient agent orchestration with effective tool usage, state management, and workflow automation.
- Observable and measurable AI application performance, quality, and reliability.
- Reduced manual workload through intelligent, task-oriented automation.
- Maintainable AI architectures that support ongoing enhancement and enterprise-scale adoption.
Ideal Candidate Profile
The ideal candidate is a senior-level software engineer with significant hands-on experience in Python, Generative AI, agentic frameworks, Google Cloud, and enterprise application integration.
Candidates must demonstrate practical experience building and deploying production AI systems rather than focusing exclusively on research, prompt engineering, or proof-of-concept development.
Experience with Google ADK is particularly valuable; however, strong engineers with demonstrated expertise in LangGraph, AutoGen, or CrewAI and the ability to rapidly adopt Google ADK will also be considered.