Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

Senior AI Engineer with 8+ years of experience building enterprise Generative AI platforms, RAG systems, AI copilots/agents, and scalable cloud-native applications. Specializes in LLM orchestration, semantic retrieval, multi-agent workflows, and production AI infrastructure using Python, LangChain, FastAPI, Kubernetes, AWS, and vector databases. Delivered AI systems supporting thousands of daily enterprise users across SaaS, healthcare, and automation platforms for US, Australia, and global remote teams.…Senior AI Engineer with 8+ years of experience building enterprise Generative AI platforms, RAG systems, AI copilots/agents, and scalable cloud-native applications. Specializes in LLM orchestration, semantic retrieval, multi-agent workflows, and production AI infrastructure using Python, LangChain, FastAPI, Kubernetes, AWS, and vector databases. Delivered AI systems supporting thousands of daily enterprise users across SaaS, healthcare, and automation platforms for US, Australia, and global remote teams.

Shie la Marie Aurigue

AI Engineer, Full Stack Developer, Back-End Developer, +4





Senior AI Engineer with 8+ years of experience building enterprise Generative AI platforms, RAG systems, AI copilots/agents, and scalable cloud-native applications. Specializes in LLM orchestration, semantic retrieval, multi-agent workflows, and production AI infrastructure using Python, LangChain, FastAPI, Kubernetes, AWS, and vector databases. Delivered AI systems supporting thousands of daily enterprise users across SaaS, healthcare, and automation platforms for US, Australia, and global remote teams.…Senior AI Engineer with 8+ years of experience building enterprise Generative AI platforms, RAG systems, AI copilots/agents, and scalable cloud-native applications. Specializes in LLM orchestration, semantic retrieval, multi-agent workflows, and production AI infrastructure using Python, LangChain, FastAPI, Kubernetes, AWS, and vector databases. Delivered AI systems supporting thousands of daily enterprise users across SaaS, healthcare, and automation platforms for US, Australia, and global remote teams.

Available to hire

Senior AI Engineer with 8+ years of experience building enterprise Generative AI platforms, RAG systems, AI copilots/agents, and scalable cloud-native applications. Specializes in LLM orchestration, semantic retrieval, multi-agent workflows, and production AI infrastructure using Python, LangChain, FastAPI, Kubernetes, AWS, and vector databases.

Delivered AI systems supporting thousands of daily enterprise users across SaaS, healthcare, and automation platforms for US, Australia, and global remote teams.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Language

English

Advanced

Work Experience

Senior Full-Stack / AI Engineer at Jellyfish

May 2, 2026 - Present

Engineered a full-stack engineering analytics platform that computes delivery metrics from GitHub, Jira, and CI/CD systems; identifies workflow bottlenecks; and provides actionable insights via role-based dashboards. Built scalable Django backends processing 50M+ engineering events daily using automated data pipelines, and optimized PostgreSQL schemas, indexing, and partitioning to reduce query latency by 65%. Developed a Python analytics engine for cycle time, lead time, deployment frequency, PR preview time, workload distribution, and bottleneck detection. Implemented high-performance REST APIs serving aggregated metrics across teams and repositories (2,000+ requests/minute) and established RBAC security across 150+ engineering teams. Built LLM-powered analytics to generate automated insights and summaries, reducing manual reporting by 70%, and delivered AI copilots for natural-language querying of performance and risks. Designed RAG architecture using Python, LangChain, FastAPI, an

Senior Full-Stack/AI Engineer at Jellyfish

May 1, 2026 - Present

Engineered a full-stack analytics platform to compute engineering delivery metrics from GitHub, Jira, and CI/CD systems. Built scalable Django backends processing 50M+ engineering events daily via automated data pipelines, and optimized PostgreSQL schemas with indexing and partitioning to reduce query latency by 65%. Developed a Python analytics engine to compute cycle time, lead time, deployment frequency, PR preview time, workload distribution, and bottleneck detection. Implemented high-performance REST APIs (DRF) serving aggregated metrics across teams and repositories (2,000+ requests/minute) and established RBAC for data access across 150+ engineering teams. Delivered LLM-powered analytics generating automated insights/summaries, reducing manual reporting by 70%, and built AI copilots enabling natural-language querying of performance metrics and risks. Designed RAG architecture using Python, LangChain, FastAPI, and Pinecone/FAISS for sub-second contextual search. Built asynchronou

Senior AI Engineer at Move Works

September 1, 2023 - Present

Architected an enterprise AI copilot and semantic search system using GPT-4, Claude, Llama, and RAG pipelines to automate internal support workflows across SaaS environments. Built scalable RAG pipelines using LangChain, LangGraph, Pinecone, FAISS, and Elasticsearch/OpenSearch with semantic retrieval frameworks, improving contextual response relevance by 35%+. Designed multi-agent AI systems integrating Slack, Microsoft Teams, ServiceNow, Salesforce, and Workday, reducing manual ticket handling time by ~40%. Improved enterprise search precision across millions of indexed documents via hybrid retrieval, embedding optimization, reranking pipelines, metadata filtering, and vector similarity search. Implemented permission-aware retrieval with RBAC-based access control, strengthening response grounding accuracy while maintaining secure enterprise document governance. Optimized LLM inference pipelines with caching layers, asynchronous workflows, and prompt execution strategies, reducing AI

Senior AI Engineer at MoveWorks

September 1, 2023 - May 1, 2026

Architected an enterprise AI copilot and semantic search system using GPT-4, Claude, Llama, and RAG pipelines to automate internal support workflows across SaaS environments. Built scalable RAG pipelines with LangChain, LangGraph, Pinecone, FAISS, and Elasticsearch/OpenSearch plus semantic retrieval frameworks, improving contextual response relevance by 35%. Designed multi-agent AI systems integrating Slack, Microsoft Teams, ServiceNow, Salesforce, and Workday, reducing manual ticket handling time by ~40%. Improved enterprise search precision across millions of indexed documents via hybrid retrieval, embedding optimization, reranking pipelines, metadata filtering, and vector similarity search. Implemented permission-aware retrieval with RBAC-based access control to improve response grounding accuracy while maintaining document governance. Optimized LLM inference pipelines using caching layers, asynchronous workflows, and prompt execution strategies, reducing AI response latency by 30%

AI Engineer at Osceer.ai

May 1, 2020 - September 1, 2023

Developed AI-powered virtual patient simulation systems supporting interactive clinical training, automated assessments, and healthcare education workflows used across thousands of simulation sessions annually. Designed NLP and conversational AI pipelines for symptom extraction, intent recognition, clinical reasoning, and contextual patient interactions using Python, spaCy, Hugging Face Transformers, and machine learning models. Built RESTful APIs and backend AI services using FastAPI to support real-time simulation workflows, patient scenario management, and concurrent assessment systems. Developed ML and conversational AI models with PyTorch and scikit-learn to improve recommendation accuracy, simulation realism, and personalized healthcare training experiences. Engineered dialogue management systems combining rule-based reasoning, NLP pipelines, and contextual response generation, reducing invalid AI responses by over 25%. Optimized PostgreSQL databases and data processing pipeline

AI Engineer at Osce r.ai

May 1, 2020 - September 1, 2023

Developed AI-powered virtual patient simulation systems supporting interactive clinical training, automated assessments, and healthcare education workflows used across thousands of simulation sessions annually. Designed NLP and conversational AI pipelines for symptom extraction, intent recognition, clinical reasoning, and contextual patient interactions using Python, spaCy, Hugging Face Transformers, and machine learning models. Built RESTful APIs and backend AI services with FastAPI to support real-time simulation workflows, patient scenario management, and concurrent assessment systems. Developed machine learning and conversational AI models using PyTorch and scikit-learn to improve recommendation accuracy, simulation realism, and personalized healthcare training experiences. Engineered dialogue management combining rule-based reasoning, NLP pipelines, and contextual response generation, reducing invalid AI responses by over 25%. Optimized PostgreSQL databases and data processing pip

Web Developer at Infinity Hub Digital Marketing

August 1, 2018 - February 1, 2020

Developed and maintained e-commerce backend systems using Python, Django, MySQL, and REST APIs supporting online product management and transaction workflows. Built inventory tracking, order processing, and administrative management services to improve operational efficiency and automate business workflows. Integrated payment gateway services and API endpoints enabling secure online transactions and reliable frontend-backend communication. Performed debugging, database optimization, deployment support, and production maintenance for scalable web applications.