Open to opportunities

Shiela Marie Aurigue

@shielamarieaurigue

Message

Senior AI engineer building enterprise GenAI, RAG, and AI copilots at scale.

Philippines

Message

What I'm looking for

I’m looking to build production-grade GenAI platforms—RAG copilots, orchestration, and secure enterprise AI—working with cross-functional teams in cloud-native environments. I want measurable impact (relevance, latency, and reliability) and room to push LLM evaluation forward.

I’m a Senior AI Engineer with 8+ years of experience building enterprise Generative AI platforms, RAG systems, AI copilots, and scalable cloud-native applications. I specialize in LLM orchestration, semantic retrieval, multi-agent workflows, and production AI infrastructure—turning advanced models into reliable, measurable outcomes for enterprise users.

At Moveworks, I architected enterprise AI copilot and semantic search systems, improving contextual response relevance by 35% and reducing manual ticket handling time by 40%. I also optimized LLM inference pipelines and deployments, cutting AI response latency by 30% under high-throughput workloads, while implementing permission-aware (RBAC) retrieval to strengthen grounding accuracy and secure document governance. Previously at Oscer.ai, I built virtual patient simulation AI for large-scale clinical training, reducing invalid AI responses by 25% and delivering production-ready FastAPI services deployed on AWS and Azure.

Experience

Work history, roles, and key accomplishments

Current

Senior AI Engineer

Current

Moveworks

Sep 2023 - Present (2 years 9 months)

Architected enterprise AI copilot and semantic search systems using GPT-4/Claude with RAG pipelines, improving contextual response relevance by 35%+. Built permission-aware retrieval with RBAC and reduced manual ticket handling time by ~40% through multi-agent integrations and optimized hybrid search.

Prompt Engineering fastAPI gRPC Kubernetes

AI Engineer

Oscer.ai

May 2020 - Sep 2023 (3 years 4 months)

Developed AI-powered virtual patient simulation systems for healthcare training, building conversational NLP pipelines and real-time simulation APIs to support thousands of sessions annually. Reduced invalid AI responses by 25%+ using dialogue management combining rule-based reasoning, NLP, and contextual generation, and improved data reliability via optimized PostgreSQL pipelines.

Conversational AI NLP Pipelines (SpaCy)PyTorch fastAPI PostgreSQL

Web Developer

Infinity Hub Digital Marketing

Aug 2018 - Feb 2020 (1 year 6 months)

Developed and maintained Python/Django e-commerce backend services for inventory tracking, order processing, and administrative workflows. Integrated payment gateway APIs, optimized database performance, and supported deployment/debugging for reliable REST API-driven transactions.

Python Django MySQL REST APIs E Commerce Backend Payment Gateways Database Optimization