Principal Tech Lead, AI Studio: Marriott International

Marriott International is the world’s largest hotel company, offering numerous brands, hotels, and opportunities for associates to grow and succeed. The company is dedicated to being an equal opportunity employer and fosters an environment where diverse backgrounds are valued and celebrated.

Position Overview & Responsibilities:
This is a temporary, full-time position focused on transforming hospitality data into an intelligent, cost-aware assistant. The role involves using hybrid Retrieval-Augmented Generation (RAG), knowledge graphs (KG), multi-tier memory, and agent-orchestrated workflows while upholding privacy, safety, and performance.

Build hybrid RAG + KG retrievers with regional embeddings.

Implement session and encrypted long-term guest memory under data retention rules.

Design model-routing and prompt-caching with real-time cost/latency dashboards.

Embed guardrails into CI/CD pipelines and lead engineers and autonomous agents.

Set prompt standards, vet agent plans, and deliver measurable gains in Net Promoter Score (NPS) and Revenue Per Available Room (RevPAR).

Requirements:

Required Qualifications:

8+ years of experience in AI and software development.

Proven success fine-tuning open-weight models (e.g., Llama-2/3, Mixtral, Phi-3) to production.

Deep grasp of knowledge graph (KG) query languages (Cypher, SPARQL) and embedding-graph fusion.

Documented experience with cost-governance (e.g., quantisation, distillation, traffic shaping).

Hands-on agent orchestration experience (e.g., Autogen, CrewAI, LangGraph).

A security-first mindset with experience sanitizing prompt logs for PII/bias.

Preferred Skills:

Published benchmarks or blogs on LLM optimization.

Experience deploying multimodal or voice interfaces at scale.