Principal Gen AI Engineer

The Role

Responsibilities:

• Lead or contribute to complex AI/ML initiatives, ensuring high-quality deliverables within software engineering environments.
• Develop and execute large-scale strategies for Generative AI capabilities, including platform architecture, engineering standards, and operational readiness.
• Design, develop, test, debug, and document AI-enabled services and applications, managing deployments across various environments.
• Architect and implement Generative AI solutions utilizing large language models (LLMs), retrieval-augmented generation (RAG), and agentic frameworks; integrate these capabilities into existing enterprise systems.
• Build production-grade agentic solutions leveraging LangChain, LangGraph, and other relevant frameworks, combining rapid composition with explicit state-machine orchestration.
• Develop multi-agent systems using Google ADK, harnessing its architecture, tool ecosystem (including MCP tools), evaluation, and deployment patterns.
• Engineer secure tool execution methods, ensuring best practices in service-to-service communication, least privilege, auditability, and enterprise standards.
• Assess and resolve moderately complex technical challenges related to AI technologies, orchestration, model behavior, and integration patterns.
• Troubleshoot and resolve issues impacting AI services and models, ensuring monitoring, operational hygiene, and risk mitigation.
• Lead the development and implementation of lifecycle tools and utilities, including evaluation metrics, quality monitoring, and drift detection.
• Collaborate with peers and stakeholders, providing guidance to less experienced team members, and promoting engineering best practices.
• Serve as a technical escalation point, driving excellence and consistency across the team.
• Ensure all engineering efforts comply with policies, procedures, security protocols, and risk management requirements.

Requirements:

• Proven experience in designing and deploying large-scale Generative AI and agentic solutions.
• Strong expertise with LLMs, RAG, LangChain, LangGraph, and multi-agent architectures.
• Hands-on experience with Google ADK and multi-agent orchestration frameworks.
• Solid understanding of secure API development, service-to-service communication, and enterprise security standards.
• Excellent problem-solving skills with the ability to evaluate complex technical challenges.
• Demonstrated leadership capabilities, mentoring skills, and experience guiding engineering teams.
• Experience with AI lifecycle management, including evaluation, monitoring, and model drift detection.
• Effective communication skills and ability to collaborate across technical and non-technical stakeholders.

Preferred, but not required:

• Experience with enterprise integration patterns.
• Knowledge of compliance, security, and risk management practices related to AI.
• Familiarity with monitoring, logging, and operational tools for AI services.