Vignesh Saptarishi Ramesh

AI systems engineering, machine learning, computational neuroscience

vignesh@traitful.ai | traitful.ai | 7rishi.io
github.com/saptaxis | linkedin.com/in/vignesh-saptarishi

10+ years designing and engineering production AI systems across computer vision, NLP, generative models, agentic workflows, and ML platform architecture. Built and led ML and data organizations, served as technical expert on enterprise sales and customer success engagements with Fortune 500 clients, and directly drove B2B revenue well into the tens of millions. Degrees in Neuroscience and Electrical Engineering. Clients include FedEx, Macy’s, Levi’s, Tata Group, HDFC Bank, Diesel, Sundaram Finance, ThredUp, Zenyum, and Dubai CommerCity.

Professional Experience

Oct 2024 - Present Founder, Traitful AI Labs

  • founded a custom AI engineering firm building production systems for enterprise clients
  • agentic AI systems and conversational AI for legal and logistics enterprises
  • production RAG pipelines with optimized search engines for agent retrieval, custom orchestration harnesses for multi-step reasoning, and memory architectures that reduce token consumption
  • chat-to-dashboard systems translating natural language into business intelligence
  • systems engineered for economic viability under real compute constraints, not big-tech budgets

Jan 2020 - Oct 2024 Director - Machine Learning, vue.ai / Mad Street Den

Built and led ML and data organizations. 100% code contributor across all projects alongside managerial responsibilities. Served as the technical expert brought onto enterprise sales and customer success calls. Key architect of the company’s DAG-based ML orchestration platform unifying vision, language, document, and generative models into scalable pipelines. Technology partnerships with Google Cloud, Meta, and Microsoft.

Intelligent Documents Processing

  • zero-to-one founding algorithms engineer for the product
  • scaled and led the ML org for domain-agnostic document processing
  • full document processing stack: OCR, document layout understanding (LayoutLM + heuristic approaches), table and figure detection, structured information extraction
  • designed retrieval-augmented workflows before “RAG” had a name, a natural extension of the semantic search systems built earlier
  • custom embeddings, re-training loops, and orchestrator as configurable workflows
  • non-LLM pipelines engineered for profitable unit economics at scale
  • deployed across government (Dubai CommerCity), BFSI (HDFC Bank, Sundaram Finance), and legal verticals
  • algorithms: LLMs (in-context learning, RAG), document layout analysis, NER, classification, embeddings, search, OCR, summarization, computer vision, multimodal AI

Virtual Dressing Room

  • pioneered GAN-based virtual try-on, among the earliest production applications of generative adversarial networks in this space
  • reframed generation as geometric deformation: regressing morphing grids, upsampling those grids, and sampling from original images for photorealistic 4K output without hallucination artifacts
  • built core networks for garment transfer, lighting, and shadow synthesis
  • designed and operated large-scale synthetic data generation pipeline: 3D modeling in Blender, garment physics simulation in CLO3D/Marvelous Designer, automated rendering across hundreds of machines with full control over lighting, materials, and environmental conditions
  • engineered human-in-the-loop production systems: models outputting Photoshop-native mesh files with separate layers for lighting and shadows, custom Photoshop plugins for in-app inference, and feedback systems capturing human corrections back into training data
  • managed 100+ person in-house data collection organization: tooling, practices, and pipeline
  • scaled up and managed a focused 6 member algorithms research team
  • algorithms: conditional GANs, spatial transformers, shadow and lighting generation, segmentation (images and video), garment and body pose/parts detection

Feb 2017 - Jan 2020 Senior ML Engineer & Technical Lead, vue.ai / Mad Street Den

Automated Product Tagging for eCommerce

  • founding algorithms engineer for the product
  • production computer vision systems for Fortune 500 retail and fashion enterprises including Macy’s, Levi’s, Diesel, and ThredUp
  • fine-grained hierarchical image classification, object detection, garment and body segmentation, and video-level scene understanding
  • cross-modal semantic search across image and text, evolving through multiple generations of embedding architectures
  • auto-generation of product titles and descriptions from images, well before language models made this mainstream
  • designed and implemented end-to-end ML workflows with automated re-training loops
  • built internal systems for no-code model building and orchestration
  • set up and scaled the data collection organization

Aug 2013 - Sep 2015 Graduate Researcher, Marder Lab, Brandeis University

  • developed spatiotemporal, physiological models to study how single neurons and neuronal circuits maintain stable behavior during growth, and in the presence of intrinsic and extrinsic perturbations
  • built a framework to configure and simulate morphologically detailed neuronal models using the NEURON simulator
  • extended the MOOSE simulator for conductance models as a Visiting Researcher at the Bhalla Lab, National Center for Biological Sciences
  • thesis: Homeostatic regulation of intrinsic neuronal conductances in morphologically growing neurons

Aug 2010 - Aug 2013 Research Associate, Waran Research Foundation, India

  • developed computational models and large-scale neural network simulators to understand implication of cellular energetics on functional brain circuits

Education

Aug 2013 - Aug 2015 M.S. Neuroscience - Brandeis University, USA

  • GPA: 3.84 / 4.00
  • graduate researcher in Prof. Eve Marder’s lab (as a PhD candidate)
  • teaching assistant - Intro to Behavioral Neuroscience, Spring 2014 with Prof. Don Katz

Sep 2009 - May 2013 B.Engg. Electrical Engineering - Anna University, India

  • first class, GPA: 8.0/10.0
  • thesis: Methods for Nonlinear Estimation using Kalman Filters to estimate state vectors and control DC motors

Fellowships & Awards

  • National Institute of Health - Neuroscience PhD Fellowship, Brandeis University, 2013-2015
  • Chairman (Devaki Muthiah) Endowment Award for Overall Best Student 2009 - 2013, Sri Venkateswara College of Engineering, Anna University