# Riddhi More **AI Solutions Architect** Toronto, Canada [Website](https://riddhimore.com/) · [LinkedIn](https://www.linkedin.com/in/riddhi-more/) · [GitHub](https://github.com/MsMore) · [Email](mailto:more.riddhi11@gmail.com) Building AI systems for enterprise workflows. ## About Riddhi More is an AI Solutions Architect in Toronto. She designs systems that connect language models with business data, APIs, and everyday workflows. Her experience spans enterprise engineering, NLP research, and teaching. At Amgen, she built agents for Legal, Finance, and Pharmacovigilance. Today, she works on AI architecture and automation at Northeast Shared Services. Her work focuses on making technology easier to understand and use. That perspective also shapes her research on efficient, reliable AI and her experience mentoring more than 500 students at Ontario Tech University. ## How Riddhi builds AI solutions ### 1. Requirements Define the business problem, user workflow, constraints, and success criteria. ### 2. Prototype Test models, retrieval, and tool integrations with a focused working prototype. ### 3. Evaluate Measure answer quality and reliability. Check failure cases, groundedness, and data leakage. ### 4. Design Plan architecture, access controls, integrations, observability, and long-term support. ### 5. Deliver Deploy, document, measure usage, and improve the system with user feedback. ## Work experience ### AI Solutions Architect — Northeast Shared Services **August 2026–Present · Canada** - Designs end-to-end AI solutions that automate business processes and improve operational efficiency. - Translates business needs into practical, scalable, and secure technical architectures. - Develops AI-powered workflows connecting cloud platforms, enterprise data, APIs, and internal systems. - Leads requirements gathering, solution design, research, prototyping, testing, and documentation. - Collaborates with business stakeholders, IT teams, subject-matter experts, and technology partners. - Evaluates security, governance, data access, traceability, scalability, and long-term support throughout the solution lifecycle. ### GenAI Engineer — Amgen **November 2025–July 2026 · Canada** - Built enterprise GenAI agents using LLMs, RAG, MCP, and agentic workflows for Legal, Finance, and Pharmacovigilance. - Designed assistants with retrieval, reasoning, tool calling, and workflow automation. - Developed RAG pipelines for document processing, embeddings, vector search, retrieval optimization, and grounded responses. - Integrated enterprise applications, APIs, Microsoft Teams, Outlook, and internal platforms through MCP-enabled agents. - Built applications and services with LangChain, Amazon Bedrock, AWS, Node.js, C#, SQL, and React. - Improved prompts, orchestration, evaluation, reliability, and hallucination reduction. - Partnered with cross-functional teams to deliver secure AI in a regulated pharmaceutical environment. ### Software and AI Researcher — Software Engineering and Education Research Lab **September 2023–November 2025 · Ontario Tech University, Canada** - Studied multilingual model realignment and layer sensitivity through ALIGNFREEZE, accepted at NAACL 2025. - Received funding to optimize LLMs for flaky test detection in resource-constrained environments. - Designed FlakyXbert with few-shot Siamese learning and explored fine-tuning, quantization, and distillation. - Worked on fairness and data-leakage safeguards for software engineering models. - Co-authored HumanEval_T, a template-based approach to benchmark generation and code-generation evaluation. - Built an agentic research assistant for literature review and knowledge management using local inference and retrieval. ### NLP Researcher — Lee Language Lab **January 2024–September 2024 · Canada** - Worked on ALIGNFREEZE, analyzing realignment in multilingual models and their internal representations. - Contributed to an evaluation framework studying alignment behavior across languages; the resulting work was accepted at NAACL 2025. ### Graduate Teaching Assistant — Ontario Tech University **September 2023–April 2025 · Oshawa, Ontario** - Mentored more than 500 students in Software Quality Assurance and Scientific Data Analysis. - Developed automated grading systems; the supplied résumé reports a 15% improvement in performance metrics. - Led weekly labs and office hours with tailored feedback; the résumé reports 95% student satisfaction. ### Globalink Research Intern — Mitacs and Ontario Tech University **June 2022–September 2022 · Canada** - Worked under Professor Jeremy Bradbury to develop Threaded Paws, a serious game for learning concurrency concepts. - Designed the learning experience for second- to fourth-year Computer Science and Software Engineering students. ### Student Technical Fellow — Google **February 2020–January 2022 · Hyderabad, India** - Selected as one of 126 participants from more than 15,000 applicants for the Women Engineers / WTEF initiative. - Completed a two-year professional development program with live sessions, boot camps, mentorship, certification, and team projects. - Developed problem-solving and computational-thinking skills through the Google-supported TalentSprint fellowship. ### MLH Fellow — Major League Hacking **June 2021–August 2021 · Distributed team** - Contributed to an open-source contribution platform using Ruby on Rails and Jekyll. - Collaborated in an agile, cross-functional, distributed team. - Worked across the software lifecycle from conception to deployment. ### International Business Consultant — X-Culture **August 2020–November 2020 · Global virtual team** - Worked in an international virtual team on business solutions for US drone company Dart Drone. - Researched markets and developed recommendations for expansion into additional countries. - Practiced global virtual collaboration across an internationally distributed team. ## Education ### Master of Science, Computer Science — Ontario Tech University **2023–2025 · GPA: 4.2/4.3** Research focus: integrating transformer-based NLP into software testing, automation, and efficiency using LLMs. Selected coursework: Advanced NLP; Research Methodologies; Software Design and Project Management. ### Bachelor of Engineering, Computer Engineering — University of Mumbai **2019–2023 · GPA: 9.11/10** Undergraduate thesis: *Automated Collision Avoidance of Unmanned Maritime Vehicles using Reinforcement Learning* (unpublished). Selected coursework: Data Structures and Algorithms; Database Management Systems; Operating Systems; Artificial Intelligence; Computer Vision; Machine Learning. ## Projects and publications ### Enterprise GenAI Agent Solutions **Category:** Enterprise **Context:** Amgen · GenAI Engineer · 2025–2026 **Technologies:** RAG, MCP, LangChain, Amazon Bedrock, Node.js, C#, SQL, React Built agentic assistants with retrieval, reasoning, tool calling, and workflow automation for regulated enterprise teams. Developed end-to-end RAG pipelines and MCP-enabled connections to enterprise APIs, Microsoft Teams, Outlook, and internal platforms. The solution design included access controls, reliability, security, and regulated business requirements. ### LLM-Powered Agentic Research Assistant **Category:** Applied AI **Context:** Research tooling · SEER Lab **Technologies:** Python, LangGraph, Ollama, FAISS, RAG, Docker, Tavily Created an end-to-end workflow for literature review and knowledge-base construction. LangGraph coordinated the workflow, Tavily supported web search, FAISS handled retrieval, and Ollama provided local model inference. The earlier portfolio reports a 65% reduction in review time. ### FlakyXbert: LLM Optimization for Flaky Test Detection **Category:** Research **Context:** SEER Lab · ICST 2025 **Technologies:** Python, BERT, PyTorch, TensorFlow, Hugging Face, few-shot learning, Siamese networks Designed a few-shot Siamese approach and compared it with fine-tuning pretrained language models on FlakyCat and IDoFT. The résumé reports more than 20% accuracy improvement and approximately 80% lower GPU usage across the project experiments; these results are context-specific. - [Paper](https://www.sqrlab.ca/publications/icst2025_flakyxbert/) - [Code](https://github.com/seer-lab/FlakyXbert) ### ALIGNFREEZE: Multilingual Model Realignment Analysis **Category:** Research **Context:** Multilingual NLP collaboration · NAACL 2025 **Technologies:** Python, PyTorch, Transformers, multilingual NLP, BERT, XLM-R Studied layer-wise changes during multilingual model realignment across three models, 35 languages, and four tasks. The work found that lower layers were particularly vulnerable to realignment and that freezing them could preserve performance when full realignment caused degradation. - [Paper](https://arxiv.org/abs/2502.12959) ### HumanEval Data Leakage Mitigation Framework **Category:** Research **Context:** SEER Lab · ICST 2025 short papers **Technologies:** Python, LLM evaluation, combinatorial testing, code generation Co-authored HumanEval_T, which uses reusable task templates and combinatorial test design to generate fresh code-generation tasks. The method reduces reliance on a fixed benchmark whose tasks and solutions may have appeared in model training data. - [Paper](https://www.sqrlab.ca/publications/icst2025_humaneval_t/) ### Assessing Data Augmentation-Induced Bias **Category:** Research **Context:** SEER Lab · FAIRNESS 2025 **Technologies:** Python, machine learning, data augmentation, model evaluation Studied how augmented training and testing samples affect model evaluation, including SMOTE and mutation-based augmentation. The work highlights the need to examine dataset construction when interpreting performance. - [Paper](https://www.sqrlab.ca/publications/fairness2025/) - [Code](https://github.com/seer-lab/AugmentationBias) ### Automated Collision Avoidance Using Reinforcement Learning **Category:** Applied AI **Context:** University of Mumbai · Bachelor's thesis · 2023 **Technologies:** Unity, ML-Agents, reinforcement learning, lidar Built a Unity simulation with lidar-derived inputs and used ML-Agents to train collision-avoidance behavior for unmanned maritime vehicles. This was an unpublished undergraduate thesis. ### Threaded Paws **Category:** Software and education research **Context:** Mitacs Globalink · Ontario Tech University · 2022 Developed a serious game for learning thread interleaving, data races, starvation, and deadlocks. The project was designed for undergraduate Computer Science and Software Engineering students. ## Technical skills ### Generative AI and agents RAG; MCP; LangChain; LangGraph; Ollama; FAISS; prompt engineering; LLM evaluation. ### Machine learning and NLP Python; PyTorch; TensorFlow; Hugging Face; multilingual NLP; few-shot learning; reinforcement learning; combinatorial testing. ### Software development TypeScript; JavaScript; React; Node.js; C#; SQL; C++; Ruby on Rails; Jekyll; Unity and ML-Agents. ### Cloud and delivery AWS and Amazon Bedrock; Docker; Git; MLOps and LLMOps; Agile and Scrum; security and governance. ## Certifications - IBM Machine Learning Specialization, 2022 - Supervised, Unsupervised and Deep Learning, 2022 - Applied Scrum for Agile Project Management, 2022 ## Contact - Email: [more.riddhi11@gmail.com](mailto:more.riddhi11@gmail.com) - LinkedIn: [linkedin.com/in/riddhi-more](https://www.linkedin.com/in/riddhi-more/) - GitHub: [github.com/MsMore](https://github.com/MsMore)