Forward Deployed Engineer, Generative AI, Google Cloud
Google View all jobs
- Mumbai, Maharashtra
- Permanent
- Full-time
- Bachelor’s degree in Science, Technology, Engineering, Mathematics, a related technical field, or equivalent practical experience.
- 8 years of experience in providing production-grade AI solutions to external or internal customers with L400-level in Python, and architecting AI systems on cloud platforms.
- Experience leading technical discovery sessions with executive stakeholders (C-suite) and engineering teams to define AI and hardware infrastructure requirements.
- Experience building full-stack solutions that interface with enterprise systems.
- Master's degree or PhD in Computer Science, AI, Machine Learning, or a related technical field.
- Experience in implementing multi-agent systems using frameworks (e.g., LangGraph, CrewAI, or Google’s Agent Development Kit (ADK)) and patterns like ReAct, self-reflection, and hierarchical delegation.
- Knowledge of Large Language Model (LLM)-native metrics (e.g., tokens/sec, cost-per-request) and techniques for optimizing state management and granular tracing.
- Ability to implement secure agentic workflows incorporating Model Context Protocol (MCP), tool-calling, and Open Authorization (OAuth)-based authentication.
- Serve as the lead developer for Artificial Intelligence (AI) applications, transitioning from rapid prototypes to production grade agentic workflows (e.g., multi-agent systems, Model Context Protocol (MCP) servers) that drive measurable Return on Investment (ROI).
- Architect and code the 'connective tissue' between Google’s Artificial Intelligence (AI) products and customer's live infrastructure, including Application Programming Interfaces (APIs), legacy data silos, and security perimeters.
- Build high-performance evaluation pipelines and observability frameworks to ensure agentic systems meet requirements for accuracy, safety, and latency.
- Identify repeatable field patterns and technical 'friction points' in Google’s AI stack, converting them into reusable modules or formal product feature requests for the Engineering teams.