AI Engineer (Agent Development Kit / ADK)

Quick Facts

• Role: AI Engineer (Agent Development Kit / ADK)

• Focus: Production-grade AI agents and multi-agent workflows

Description

Build production-grade AI agents and multi-agent workflows using Google’s Agent Development Kit (ADK). Integrate agents with enterprise data sources and business tools, then deploy and scale them on Google Cloud while evaluating and tuning performance for latency and cost. You’ll also create observability, testing, and safety guardrails so agent behavior is reliable and predictable in production.

Responsibilities

• Design and build AI agents and multi-agent workflows using ADK

• Implement agent orchestration patterns: tool use, function calling, sub-agent delegation, and state/session management

• Integrate agents with enterprise data sources (e.g., Snowflake, Salesforce) and internal APIs

• Deploy and scale agents on Google Cloud (Vertex AI Agent Engine or equivalent)

• Evaluate and tune agent performance, latency, and cost across model backends

• Build tooling and guardrails (observability, testing, safety checks)

• Collaborate with data engineering and platform teams to expose reliable, well-governed data

Requirements

• 8+ years of software engineering experience, with recent focus on applied AI/agent systems

• Hands-on experience building agents with Google ADK (or comparable agent frameworks such as LangGraph, AutoGen, CrewAI, with strong ability to ramp on ADK)

• Strong Python development skills

• Experience with LLM APIs (Gemini, Claude, OpenAI, or similar) and prompt/tool design

• Understanding of agent architecture patterns: planning, tool orchestration, memory/state, multi-agent coordination

• Experience with REST APIs and backend service integration

• Familiarity with Google Cloud Platform (Vertex AI, Cloud Run, IAM, Secrets Manager)

• Proven ability to ship AI features to production

• Comfortable working independently in ambiguous, fast-evolving technical territory

• Clear communication skills to explain agent behavior and architecture to technical and non-technical stakeholders

Benefits

• Agents that are reliable, observable, and behave predictably in production

• Clean integration between agents and underlying enterprise data/systems

• Reduced manual effort for end users through well-scoped agent automation