I'm Nirav Patel, an AI/LLM Engineer based in Toronto, Ontario, with 3+ years of experience designing and delivering production-grade, cloud-native AI systems. I specialize in LLMs, Generative AI, Retrieval-Augmented Generation (RAG), and agentic workflows using Python, FastAPI, LangChain/LangGraph, and vector databases across AWS, GCP, and Azure. I'm passionate about turning complex business problems into scalable, governance-friendly AI solutions. I thrive in cross-functional teams, collaborating with product, UX, and platform engineering to ship reliable, measurable, and high-impact AI products while upholding responsible AI practices and strong observability.

NIRAV PATEL

I'm Nirav Patel, an AI/LLM Engineer based in Toronto, Ontario, with 3+ years of experience designing and delivering production-grade, cloud-native AI systems. I specialize in LLMs, Generative AI, Retrieval-Augmented Generation (RAG), and agentic workflows using Python, FastAPI, LangChain/LangGraph, and vector databases across AWS, GCP, and Azure. I'm passionate about turning complex business problems into scalable, governance-friendly AI solutions. I thrive in cross-functional teams, collaborating with product, UX, and platform engineering to ship reliable, measurable, and high-impact AI products while upholding responsible AI practices and strong observability.

Available to hire

I’m Nirav Patel, an AI/LLM Engineer based in Toronto, Ontario, with 3+ years of experience designing and delivering production-grade, cloud-native AI systems. I specialize in LLMs, Generative AI, Retrieval-Augmented Generation (RAG), and agentic workflows using Python, FastAPI, LangChain/LangGraph, and vector databases across AWS, GCP, and Azure.

I’m passionate about turning complex business problems into scalable, governance-friendly AI solutions. I thrive in cross-functional teams, collaborating with product, UX, and platform engineering to ship reliable, measurable, and high-impact AI products while upholding responsible AI practices and strong observability.

See more

Experience Level

Expert
Expert
Expert
Expert
Expert
Intermediate

Language

English
Fluent

Work Experience

AI Engineer at Subprime Platforms Inc.
April 1, 2025 - Present
Led AI initiatives for DeepIDV, architecting ML/LLM pipelines and RAG services for 600+ users; improved self-serve resolution by 30% and retrieval quality by 35% using embeddings, vector DBs, and NLP under strict data governance. Built low-latency Python inference pipelines (FastAPI + vector DB) on GCP (Vertex AI, Gemini), reducing median response time by 45% to 350 ms and improving answer relevance by 25% in production. Implemented MLOps/LLMOps (Git, GitHub Actions, model versioning, promotion/rollback), and introduced AI-assisted development with prompt templates and guardrails, reducing feature delivery time by 20-25%. Established end-to-end monitoring and observability (latency, quality, cost, drift) for AI services and mentored juniors on ML/NLP/LLM integration.
Data Analyst at Digital Pilot
December 1, 2021 - October 1, 2022
Developed automated data pipelines in SQL and Python for marketing and sales analytics, reducing manual reporting effort by 60-70%. Created Power BI dashboards for real-time campaign and revenue performance, boosting self-serve analytics adoption to 20+ stakeholders and cutting decision cycles from weekly to daily.
Software Engineer at Thingslista Automation LLP
November 1, 2020 - November 1, 2021
Engineered automation systems and internal REST APIs using PLCs, Python, Django, and PostgreSQL to integrate automation hardware with internal tools, reducing manual operational effort by 75% and improving data reliability/throughput by 30%. Led deployment, testing, documentation, and end-user training, cutting onboarding time by 25% and reducing support requests from operations teams.

Education

Data Analysis for Business Decision Making at Durham College
January 1, 2024 - January 1, 2024
Artificial Intelligence Analysis, Design & Implementation at Durham College
January 1, 2023 - January 1, 2023
Bachelor of Engineering – Information Technology at GTU
January 1, 2016 - January 1, 2020

Qualifications

Add your qualifications or awards here.

Industry Experience

Software & Internet, Professional Services, Computers & Electronics
    paper AI-Task-Architect

    The AI Task Architect is a dual-backend AI application that takes natural language prompts like:

    “Fetch Tesla stock price every morning and post to Slack.”

    and generates a valid, executable n8n workflow JSON using the OpenAI API.

    🔧 Core Features
    ✅ FastAPI-powered AI backend with OpenAI function calling
    ✅ NestJS Gateway with typed DTOs and error handling
    ✅ Generates clean, importable n8n workflows (name, nodes, connections)
    ✅ SQLite database integration for workflow history and reuse
    ✅ JSON structure repair, enrichment, and validation