
Yash Desai
Senior Full Stack AI/ML Engineer | Python · AWS · FastAPI · Cloud Architecture
Hire this person
Send a job offer directly to this candidate
About
Senior Full Stack Engineer with 8+ years of experience designing, building, and deploying production-grade software systems across AI/ML, cloud-native backend architecture, and modern web applications. Led teams of 6-10 engineers delivering enterprise SaaS products serving real customers. Deep hands-on expertise building scalable Python and FastAPI services, AI-powered applications, LLM integrations (OpenAI, Claude, Groq, Ollama), and AWS-based production infrastructure.
Architected complete on-premise LLM infrastructure including QLoRA fine-tuning, GGUF optimization, and privacy-first inference. Specialized in Generative AI, Agentic AI, Retrieval-Augmented Generation (RAG), MCP (Model Context Protocol) servers, prompt engineering, tool calling, and enterprise AI workflow automation. Experienced in cloud infrastructure (AWS, Docker, Cloudflare), microservices architecture, CI/CD pipelines, and asynchronous backend systems.
Proven track record of delivering AI-powered business automation platforms, enterprise IoT systems, and production REST APIs while mentoring junior developers and collaborating directly with clients on architecture and product strategy.
Experience
Senior AI Systems Developer & Team Lead - Consult Anubhav
(2023-08)
Lead a team of 6-10 developers designing, building, and maintaining production SaaS platforms — WhatsApp CRM (WhatsEase) and AI-powered social media automation (Krosspost.ai) — serving active paying customers
- Architected and developed AI-powered backend services using Python, FastAPI, Node.js, and React, integrating LLMs into enterprise business workflows
- Built production AI pipelines for Retrieval-Augmented Generation (RAG), prompt engineering, tool calling, and local/private LLM deployments using Ollama, Groq, and OpenAI
- Designed and deployed complete on-premise LLM infrastructure including QLoRA fine-tuning, LoRA adapter management, GGUF model conversion, and privacy-first inference environments
- Developed custom MCP (Model Context Protocol) servers enabling enterprise AI agents to securely communicate with internal databases, third-party APIs, and business systems
- Implemented complex agentic AI workflows for enterprise clients where low-code automation platforms were insufficient, delivering custom automation solutions
- Built Google Workspace Add-ons and Chrome Extensions for enterprise workflow automation and payment collection
- Containerized all services with Docker and Docker Compose, managed cloud deployments on AWS, and configured production monitoring
- Reviewed AI-generated code, established engineering standards and best practices, mentored junior developers, and collaborated directly with clients on architecture decisions and product roadmaps
Senior Web Developer & Technical Lead - WeEnggs Technology - Surat, Gujarat
(2021-06 - 2023-08)
Led development of Gosetu, an enterprise textile IoT platform providing real-time machine monitoring, live analytics, and production reporting
- Designed scalable backend systems using Node.js (Express.js), TypeScript, and relational databases, serving high-volume industrial sensor data
- Built responsive React.js dashboards with Redux for real-time visualization of live manufacturing metrics
- Optimized MySQL database schema, query performance, and indexing strategies, improving application performance by over 60%
- Implemented CI/CD pipelines with GitHub Actions, automated production deployments, and established development best practices across the team
- Mentored junior engineers on code quality, system design, and modern web development practices
Full Stack Web Developer & Consultant - Independent Freelance Developer
(2015-07 - 2021-06)
- Delivered 50+ production web applications across healthcare, education, e-commerce, and business automation domains for domestic and international clients
- Managed complete project lifecycle from requirement gathering and architecture planning through deployment, testing, and long-term client support
- Built secure REST APIs, backend services, payment gateway integrations, reporting dashboards, and scalable business applications using the MERN Stack (MongoDB, Express.js, React.js, Node.js) and LAMP Stack (Linux, Apache, MySQL, PHP)
- Worked directly with clients to translate business requirements into technical architecture and delivered solutions on time within budget constraints
Computer Lab Assistant & Programming Instructor - Narmada College of Science & Commerce
(2018-06 - 2020-02)
- Instructed students in C, C++, Java, Web Development, and MySQL, building foundational programming skills
- Managed laboratory infrastructure supporting 100+ students, maintained computer systems and network operations
- Provided individual mentorship to students on software development projects and programming concepts
Education
B.Sc. - Computer Science - Narmada College of Computer Application (NCCA) (2015 - 2018)
