I build AI systems that work in the real world — robotics, vision-language-action (VLA) systems, industrial troubleshooting, clinical decision support, retrieval systems, and conversational interfaces. My work blends AI, software engineering, and human-centered design.

I specialize in:

• Retrieval-Augmented Generation (RAG)
• Agentic workflows for real tasks
• Vision-Language-Action (VLA) systems & social robotics
• Model optimization (local inference, llama.cpp)
• Conversational systems & search interfaces
• Evaluation of human–AI decision-making & reliance

I care about making AI useful, reliable, and understandable — and increasingly about Responsible AI, the focus of my incoming master's research.

Building demand-driven forecasting and applied ML systems for production and capacity planning (current role, since June 2026).

• Built PathAI's first customer-facing cost dashboard, shipped in AiSight Dx v2.18
• Scoped the MVP with design and customer success, translating customer needs into prioritized requirements
• Cut delivery time from ~3 months to ~1 month using Django, Vue, and AI-assisted development

A full RAG + agent pipeline running inside a Furhat social robot.

• Adaptive + Corrective + Self-RAG (improved accuracy ~15%)
• Sub-8s on-device inference with llama.cpp (~15% lower cloud costs)
• Dockerized FastAPI services on AWS EC2 (sub-4s end-to-end latency)
• Powered NorwAI's first robot-connected backend

AI system for frontline industrial operators.

• First agent shipped within the "Atlas" Industrial AI platform
• 90% document parsing accuracy (embeddings + cross-encoders)
• Gemini multimodal integration for GCP customers
• Tail-generation summarization for long-context handling (~5% fewer tokens)

• 90% X-ray classification accuracy (CNNs + Vision Transformers)
• RAPTOR-based retrieval pipeline (95% medical retrieval accuracy)
• Personalized rehab guidance grounded in medical literature (RAG)
• Co-authored & presented at CUCAI 2024

• Designing online experiments on appropriate human–AI reliance in subjective decision-making (SHARE Lab, Sharon Ferguson)
• Built a closed LLM chat environment in Qualtrics to observe reliance behaviors
• First-author CHI / CUI submission
• Conversational search & recommendation systems research (Mark Smucker)

• Austin, Texas — Industrial AI (Cognite)
• Boston, Massachusetts — Cost dashboards & product tooling (PathAI)
• Trondheim, Norway — Robotics + RAG research (NorwAI, NTNU)
• Toronto, Ontario — Clinical AI, startup engineering, applied ML (XCare, Genellipse, Approva, D&I Integrators) + banking QA automation (TD)
• Waterloo, Ontario — Research + engineering degree (UWaterloo)
• Vancouver, BC — Early software & customer-facing work

These experiences shaped my ability to work across diverse cultures, industries, and technical stacks.

Outside of my AI/ML work, I've also built:

• Full-stack MERN applications (startup/fintech — Approva, Techstars)
• Banking automation testing frameworks (TD — Java Selenium, Jenkins, ~58% faster runtime)
• Database + vector search systems (MongoDB redesigns — Genellipse)
• Predictive analytics tools and dashboards
• Production CI/CD pipelines (Jenkins, Firebase, Supabase)

A lot of my breadth comes from working across startups, industry, research labs, and enterprise environments.

👉 For my full work experience and detailed career history, check my LinkedIn: https://linkedin.com/in/jeevan-parmar-62b464194

AI / ML: PyTorch, HuggingFace, RAG, Agents, VLA systems, OpenAI, Gemini, llama.cpp Backend: FastAPI, Django, Node.js, Docker, AWS/GCP/Azure, microservices Full-Stack: React, Vue, TypeScript, Express, SQL/NoSQL Infra / Tools: ChromaDB, Supabase, Jenkins, Firebase Specialties: Model optimization, conversational systems, applied ML research

• Search Engine (BM25 + embeddings): Query-biased summaries + statistical evaluation
• Audio Transcriber: Whisper + GPT cleaning pipeline with HITL workflows
• Meal Stream: Full-stack meal planning + nutrition analytics
• Energy Price Forecasting: ML models for PJM market prediction
• NBA Player Projection: Live model deployment w/ analytics dashboard

I'm a University of Waterloo Engineering alum — BASc in Management Engineering (Computing Option), where I focused on:

• Machine Learning
• Optimization
• HCI
• Software engineering
• Systems design
• Decision analysis

I'm now an incoming MASc student at Waterloo, specializing in Responsible AI and Vision-Language-Action (VLA) systems. My academic work includes CHI-focused research and building conversational/agentic systems.

I train Brazilian Jiu-Jitsu, run marathons, play football (both), basketball, squash, tennis, and golf. I also enjoy collecting colognes and watching absurdly long sports documentaries.

• LinkedIn: https://linkedin.com/in/jeevan-parmar-62b464194
• GitHub: https://github.com/jeevanp03
• Email: j29parma@uwaterloo.ca