Shivani Bhawsar
Senior Machine Learning Engineer @Handel Architects
Signup · Get unlimited contacts
WORK HISTORY
Senior Machine Learning Engineer @Handel Architects
New York, NY, US
Led development of AI-driven computational design systems, building end-to-end ML pipelines from multimodal data ingestion to model training, evaluation, and production deployment.• Built Unit Finder, a spatial retrieval engine for architectural floor plans using geometric embeddings and nearest-neighbor similarity search, reducing manual design comparison time by 90% and enabling scalable layout similarity discovery; resulted in research publication.• Developed Construction Documentation Finder, an LLM-powered semantic search platform for BIM drawings using embeddings, vector retrieval, and RAG pipelines, reducing document retrieval time by 85%.• Trained and fine-tuned diffusion models using LoRA for sketch-to-render generation, reducing manual visualization turnaround time by 70% and enabling controllable multimodal design exploration.
EDUCATION
Rajasthan Board of Secondary Education
12th, Computer Science
College of Technology And Engineering
Bachelor of Technology, Computer Science & Engineering
Stevens Institute of Technology
Master's degree, Artificial Intelligence
ABOUT SHIVANI BHAWSAR
Portfolio - https://shivanibhawsar.com/Machine Learning Engineer with 8+ years of experience building large-scale production ML systems, generative AI models, and multimodal retrieval pipelines. My work spans LLMs, diffusion models, RAG architectures, and computer vision across both industry and scientific research. Currently, I develop AI-driven computational design systems, including embedding-based retrieval for architectural layouts, LLM-powered semantic search for BIM drawings, and diffusion-based generative models for controlled architectural rendering. My research focuses on multimodal representation learning and scientific AI. I have published in MRS Bulletin and Journal of Physics D, and worked as a visiting researcher at Harvard Medical School and Stevens Institute of Technology on disease modeling, biomarker discovery, and generative modeling for nanomaterials. Selected work includes: • ArchVisMix — controlled generative architecture rendering using diffusion + structural priors • Multimodal tagging and ranking of artistic images (Behance dataset) • OpticalGPT — diffusion-based crystal structure generation (patent filed) • Ordinal latent modeling for Type 1 Diabetes biomarker discovery Interested in Machine Learning Engineer and Research Scientist roles focused on generative AI, multimodal learning, and large-scale ML systems.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.