1 day ago
Bengaluru, IndiaStaff+
Responsibilities
- Define reference architectures and technical standards for GenAI applications, RAG systems, agent ecosystems, data pipelines, LLMOps, security, observability, and cost control on GCP.
- Architect and lead production GenAI and agentic AI implementations using Vertex AI, ADK, grounding, pipelines, evaluation, planning, tools, memory, and human-in-the-loop workflows.
- Drive end-to-end data ingestion, indexing, cloud service, event, and near-real-time or batch pipeline delivery across teams.
- Build reusable prompt libraries, tool catalogs, agent templates, evaluation harnesses, productized APIs, and organization-wide AI platform capabilities.
- Standardize model and agent CI/CD, registries, traceability, rollback, canary releases, cost and performance monitoring, and operational scorecards.
- Implement guardrails, privacy and PII controls, data residency, tenant isolation, auditability, and security policies for responsible AI and regulatory readiness.
- Mentor senior engineers and team leads, lead architecture reviews and red-team exercises, and align roadmaps and operational practices with Product, Security, and SRE.
Requirements
- 12–15+ years of experience in software, data, or ML engineering, including at least 1 year of hands-on LLM, GenAI, and agentic systems experience.
- Proven delivery of enterprise-scale GenAI or agent platforms on GCP, including Vertex AI, BigQuery, Cloud Run, Pub/Sub, and Workflows.
- Demonstrated impact in platformization, governance, multi-team technical leadership, and security-by-design, privacy, or compliance audits.
- Strong proficiency in Java.
- Strong proficiency in Python or TypeScript, or equivalent, plus infrastructure-as-code using Terraform or GCP Deployment Manager.
- Experience developing data pipelines with Dataflow, Apache Beam, Spark, or similar distributed computing frameworks.
- Experience with model selection, prompt engineering, RAG and grounding, multimodal pipelines, fine-tuning or adapter methods, agent loops, planners, tools, memory, and policy enforcement.
- Experience with BigQuery vector functions, Vertex Vector Search, Document AI, Dataplex, Vertex AI Pipelines, LLMOps or MLOps, IAM, Secret Manager, VPC-SC, private service connect, DLP, Okta/IAP, Apigee, observability, and cost or capacity planning.
- Strong SQL proficiency for data analysis.
Tech Stack
Categories
About Sabre
Sabre builds software and services for the global travel industry, including an airline and hotel commerce platform and a global distribution system connecting travel suppliers with agencies and corporate buyers. It sells enterprise SaaS and transaction-based distribution services used to retail, distribute, and fulfill flights and hotel stays. Founded in 1960 and headquartered in Southlake, Texas, it serves airlines, hoteliers, online travel agencies, and corporate travel programs worldwide.