Principal GenAI & Agentic AI Engineer

The Principal GenAI & Agentic AI Engineer is the technical leader responsible for designing, building, and scaling AI systems that combine LLM-powered GenAI and ADK-based agentic workflows on Google Cloud Platform. This role also requires leading and developing data pipelines for necessary data layer for AI/ML. This role sets architecture standards, leads multi-team delivery, and governs safety, reliability, and cost at enterprise scale—accelerating product teams to achieve monetization of AI based products through reusable patterns, platforms, and guardrails. 

Key Responsibilities 

Strategy & Architecture 

• Define reference architectures for GenAI apps, RAG systems, and agent ecosystems (single/multi-agent) on GCP using ADK. 

• Leverage capabilities of Gemini Enterprise Agent Platform in the Agentic AI Product development. 

• Establish domain and platform standards: model selection, RAG/generation patterns, memory architectures, security baselines, observability, and LLMOps. 

• Lead portfolio-wide technical decisions (build/buy, vendor selection, SLAs, quotas) with a focus on reliability, safety, and cost control. 

• Define the data pipeline development for lakehouse, delta lake or feature engineering. 

Solution Design & Delivery 

• Architect and lead implementation of production-grade GenAI solutions (Vertex AI models, Grounding, Pipelines, Evaluation) and agentic services (planning, tools, memory, HIL). 

• Design multi-tenant and hub-and-spoke patterns with Okta/IAP/Apigee for secure API exposure and tenant isolation. 

• Drive end-to-end delivery across teams: data ingestion (Dataflow/Composer), indexing (BigQuery vectors/Vertex Vector Search), services (Cloud Run/Workflows), events (Pub/Sub). 

• Data Pipeline both near real time and batch. 

Platformization & Reuse 

• Build and maintain prompt libraries, tool catalogs, agent templates, and evaluation harnesses for organization-wide reuse. 

• Standardize LLMOps: CI/CD for prompts/models/agents, model registry, traceability, rollback, canaries, cost/performance scorecards. 

• Enable a marketplace of agents/services with productized APIs, documentation, chargeback, and KPIs. 

Responsible AI, Security & Compliance 

• Implement multi-layer guardrails: policy prompts, filters, memory governance, tool whitelisting, audit logs; ensure regulator-ready posture. 

• Codify privacy, PII handling, data residency, and per-tenant isolation using VPC-SC, Secret Manager, IAM, and Apigee policies. 

Leadership & Enablement 

• Mentor senior engineers and team leads; run architecture reviews, design clinics, and red-team exercises. 

• Drive continuous evaluation programs and publish org scorecards for quality, safety, and cost. 

• Partner with Product, Security, and SRE to align roadmaps, SLOs, and operational playbooks. 

Required Technical Competencies  

• Dataflow and Apache Beam for data pipeline development. 

• Strong on using SQL for data analysis. 

• LLM & GenAI: Model selection (Gemini & Model Garden), prompt engineering, RAG/grounding, multimodal pipelines, fine-tuning/adapter methods. 

• Agentic AI (ADK): Agent loops, planners, tool/function design, memory (episodic/semantic/long-term), HIL, policy enforcement. 

• Data & Retrieval: BigQuery (including vector functions), Vertex Vector Search, Document AI, Dataplex for lineage and governance. 

• Orchestration & Services: Cloud Run, Workflows, Pub/Sub, Dataflow/Composer; HA/DR, backpressure, circuit breakers. 

• LLMOps/MLOps: Vertex AI Pipelines, registry, CI/CD, trace correlation, cost/performance monitoring. 

• Security & Compliance: IAM, Secret Manager, VPC-SC, private service connect, DLP, Okta/IAP, Apigee API policies. 

• Observability & Cost: Central telemetry, user feedback loops, drift/outlier detection, quota/capacity planning. 

Qualifications 

• 12–15+ years in software/data/ML engineering; 1+ years hands-on with LLMs/GenAI and agentic systems. 

• Proven delivery of enterprise-scale GenAI/agent platforms on GCP (Vertex AI, BigQuery, Cloud Run, Pub/Sub, Workflows). 

• Demonstrated impact in platformization, governance, and multi-team technical leadership. 

• Strong proficiency in Java. 

• Strong proficiency in Python/TypeScript (or equivalent) and infrastructure-as-code (Terraform/GCP Deployment Manager). 

• Experience in security-by-design, privacy, and compliance audits. 

• Proven delivery in building data pipeline using distributed computing frameworks such as Dataflow, Spark.