Forward Deployed Engineer III, Google Cloud, Applied AI

• Serve as the lead developer for conversational artificial intelligence (AI) and customer experience (CX) applications, transitioning from rapid prototypes to production-grade agentic workflows.
• Architect and code conversational flows that are not just functional, but optimized for the "connective tissue" between Google’s Conversational AI products and customers’ live infrastructure, including APIs, legacy data silos, and security perimeters.
• Build high-performance evaluation (Eval) pipelines and observability frameworks to optimize agentic workloads, focusing on reasoning loops, tool selection, and reducing latency while maintaining production-grade security and networking.
• Identify repeatable field patterns and technical "friction points" in Google’s AAI stack, converting them into reusable modules or product feature requests for Engineering teams.
• Co-build with customer engineering teams to instill Google-grade development best practices, ensuring long-term project success and high end-user adoption.

Minimum qualifications:

• Bachelor’s degree in Engineering, Computer Science, a related field, or equivalent practical experience.
• 5 years of experience with software development using Python or similar coding languages.
• Experience architecting AI systems on cloud platforms (e.g., GCP).
• Experience deploying resources via Terraform or similar tools to automate the setup of agents, functions, or networking.
• Experience building full-stack applications that interact with enterprise IT infrastructures and developing external customer projects.

• Master’s degree or PhD in AI, Computer Science, or a related technical field.
• Experience implementing multi-agent systems using frameworks like ReAct and self-reflection.
• Experience debugging Agent logic and optimizing tool selection, including tracing conversation IDs across microservices to identify and resolve failures in real-time.
• Experience connecting agents to enterprise knowledge bases and optimizing RAG chunking to prevent hallucinations.
• Ability to travel up to 50% of the time.
• Track record of troubleshooting live, high-traffic systems during critical windows.