About this role
The Principal GenAI & Agentic AI Engineer is a technical leader responsible for designing and scaling LLM-powered applications and ADK-based agentic systems on Google Cloud Platform. The role also leads development of the data pipelines supporting AI/ML products. It sets enterprise architecture standards and helps product teams deliver reusable, reliable, safe and cost-conscious AI capabilities for the travel industry.
Responsibilities
- Define reference architectures for GenAI applications, RAG systems and single- or multi-agent ecosystems. Set standards for model selection, retrieval, memory, security, observability and LLMOps; guide build-versus-buy decisions, vendor selection, SLAs and quotas.
- Lead delivery of production GenAI and agentic services using Vertex AI and Gemini Enterprise Agent Platform capabilities, including grounding, evaluation, planning, tools, memory and human-in-the-loop workflows. Design secure multi-tenant APIs and tenant isolation.
- Direct near-real-time and batch data pipelines, ingestion, vector indexing, services and event workflows. Develop reusable prompt libraries, tool catalogs, agent templates and evaluation harnesses, along with CI/CD, traceability, rollback, canaries and cost/performance scorecards.
- Establish privacy, PII, data-residency and audit controls; mentor engineers, lead architecture reviews and red-team exercises, and work with Product, Security and SRE on roadmaps, SLOs and operational practices.
Required qualifications
- 12–15+ years in software, data or ML engineering and 1+ years of hands-on LLM/GenAI and agentic-systems experience. Proven delivery of enterprise-scale GenAI or agent platforms on GCP, distributed data pipelines, platform governance and multi-team technical leadership.
- Strong Java proficiency; strong Python or TypeScript proficiency (or equivalent); infrastructure-as-code experience with Terraform or GCP Deployment Manager; and experience with security-by-design, privacy and compliance audits.
- Technical competencies include Dataflow, Apache Beam, SQL, BigQuery, Vertex Vector Search, Document AI, Dataplex, Cloud Run, Workflows, Pub/Sub, Vertex AI Pipelines, and distributed frameworks such as Spark. The role calls for prompt engineering, RAG, multimodal pipelines, fine-tuning methods, agent design, LLMOps/MLOps, observability and cloud security controls.
Location and arrangement: India - Bangalore-Navigator Bldg; hybrid.
Skills for this role
Generative AILarge Language ModelsAI agentsGoogle Cloud PlatformAgent Development KitGeminiGemini Enterprise Agent PlatformVertex AIRetrieval-Augmented GenerationPrompt engineeringMultimodal AIFine-tuningDataflowApache BeamSQLBigQueryVertex Vector SearchDocument AIDataplexCloud ComposerCloud RunGoogle Cloud WorkflowsPub/SubVertex AI PipelinesLLMOpsMLOpsCI/CDJavaPythonTypeScript Spark HIL