Skip to main content

Pritesh Kanani

Founder and Chief Executive Officer, Acasa Labs

Full-stack and AI engineer. Builds the product and the automation inside it.

Pritesh Kanani is the founder of Acasa Labs and a full-stack and AI engineer with more than eight years of experience building AI-powered applications and data-intensive systems. He specialises in LLM integration, retrieval-augmented generation, and Python backends, and takes products from zero to production while balancing performance, accuracy, and cost. He has worked in India and Canada, and is based in Surat.

Pritesh Kanani

Expertise

  1. 01

    RAG and LLM products

    Retrieval pipelines with embeddings and vector databases, chunking strategies for long documents, and routing across several LLM providers to balance cost, latency, and answer quality.

  2. 02

    Model training and evaluation

    Fine-tuning 7 to 13 billion parameter models, including Dolly 2.0, LLaMA 2, and Falcon, on domain data with resource-efficient techniques, and evaluating model output for accuracy and bias.

  3. 03

    Python backends and full-stack apps

    FastAPI, Django, and Django REST Framework backends with Next.js and React frontends, authentication and authorization, and real-time monitoring of high-volume data.

  4. 04

    Machine learning and data

    PyTorch, TensorFlow, and scikit-learn for classification, segmentation, and clustering, and large-dataset processing with Spark, Dask, and BigQuery.

Experience

  • Acasa Labs

    Founder

    Surat, India

    Runs the studio and its products, and builds client work across web, mobile, and AI.

  • NoteTube, Inc.

    Forward Deployed AI Engineer

    Dec 2024 – present · Delaware, United States (remote)

    Architected and built the AI learning platform end to end: document and video ingestion, RAG over vector search, chunking for long academic documents, multi-provider LLM routing, and the architecture, model, and deployment decisions from zero to production.

    NoteTube case study

  • Ontario Power Generation

    Quantitative Methods Analyst

    Nov 2023 – Nov 2024 · Pickering, Canada

    Built Django web application features, added a small LLM to summarize letter threads, and rebuilt a data-critical MS Access application as a full-stack Django REST Framework and Next.js app.

  • Lamina Solutions

    Machine Learning Engineer (intern)

    May 2023 – Aug 2023 · Toronto, Canada

    Fine-tuned Dolly 2.0 and LLaMA models with 4-bit and 8-bit precision, evaluated response quality, built domain training sets, and ran document embedding for RAG with ChromaDB and Pinecone.

  • Logilite Technologies

    Software Developer (full stack)

    Nov 2018 – Jul 2022 · Ahmedabad, India

    Built a multi-tier authentication system and REST API for ML model integration, and led a React and Django real-time monitoring and alerting application for the oil and gas industry.

Education

  • George Brown College

    Postgraduate diploma, Applied AI Solution Development

    2022 – 2023 · Toronto, Canada

  • Gujarat Technological University

    Bachelor of Engineering, Instrumentation and Control

    2014 – 2018 · Ahmedabad, India

Products he runs at Acasa Labs

  • NoteTube

    A lecture becomes a study system: chat, flashcards, quizzes, all grounded in the source.

  • Kraftr

    One flat-lay photo becomes catalog-ready 4K on-model imagery.

  • Pullsy

    Instagram analytics that keep the numbers Instagram throws away.

  • GymFast

    Members, billing, classes, and workout plans for a gym, in one platform and three apps.

  • SigmaCPM

    Construction project management where AI reads the tender and shows its work.

Work with Pritesh

Bring the problem. He will tell you what he would build.

Thirty minutes on how the work happens today. You leave with a written plan: scope, timeline, and a number.

Start a conversation

No pitch deck. You own the code from day one.

contact@acasalabs.com