Looks like you have JavaScript disabled. For the full Twine experience, you will need to re-enable it.

AI/ML engineer focused on building end-to-end LLM-powered products, production RAG pipelines, and multi-agent systems for real-world enterprise use. I design reliable tool-using agent architectures, evaluate models for accuracy/compliance, and deploy scalable services across AWS/GCP with strong engineering practices. I work across the stack—data ingestion, model inference, structured extraction, and API-backed microservices—optimizing cost/latency and improving quality through systematic evaluation. I also collaborate with teams to integrate AI into production environments with well-documented architectures and safe, responsible AI practices.…AI/ML engineer focused on building end-to-end LLM-powered products, production RAG pipelines, and multi-agent systems for real-world enterprise use. I design reliable tool-using agent architectures, evaluate models for accuracy/compliance, and deploy scalable services across AWS/GCP with strong engineering practices. I work across the stack—data ingestion, model inference, structured extraction, and API-backed microservices—optimizing cost/latency and improving quality through systematic evaluation. I also collaborate with teams to integrate AI into production environments with well-documented architectures and safe, responsible AI practices.

Tejas Dharani

AI Engineer, Back-End Developer, Full Stack Developer, +2





AI/ML engineer focused on building end-to-end LLM-powered products, production RAG pipelines, and multi-agent systems for real-world enterprise use. I design reliable tool-using agent architectures, evaluate models for accuracy/compliance, and deploy scalable services across AWS/GCP with strong engineering practices. I work across the stack—data ingestion, model inference, structured extraction, and API-backed microservices—optimizing cost/latency and improving quality through systematic evaluation. I also collaborate with teams to integrate AI into production environments with well-documented architectures and safe, responsible AI practices.…AI/ML engineer focused on building end-to-end LLM-powered products, production RAG pipelines, and multi-agent systems for real-world enterprise use. I design reliable tool-using agent architectures, evaluate models for accuracy/compliance, and deploy scalable services across AWS/GCP with strong engineering practices. I work across the stack—data ingestion, model inference, structured extraction, and API-backed microservices—optimizing cost/latency and improving quality through systematic evaluation. I also collaborate with teams to integrate AI into production environments with well-documented architectures and safe, responsible AI practices.

Available to hire

AI/ML engineer focused on building end-to-end LLM-powered products, production RAG pipelines, and multi-agent systems for real-world enterprise use. I design reliable tool-using agent architectures, evaluate models for accuracy/compliance, and deploy scalable services across AWS/GCP with strong engineering practices.

I work across the stack—data ingestion, model inference, structured extraction, and API-backed microservices—optimizing cost/latency and improving quality through systematic evaluation. I also collaborate with teams to integrate AI into production environments with well-documented architectures and safe, responsible AI practices.

Skills

Experience Level

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Expert

Intermediate

Beginner

Beginner

Language

English

Advanced

Work Experience

Developer — Forage AI at Forage AI

July 1, 2025 - Present

Architected and deployed end-to-end LLM-powered microservices for enterprise partners, covering data ingestion to structured delivery, using PyTorch, LangGraph, Playwright, MCP, FastAPI, Docker, and AWS/GCP. Evaluated proprietary and open-source LLMs (including Llama 3) across cost, latency, and accuracy trade-offs in partnership with client engineering teams. Built production RAG pipelines for sub-10-second query performance over thousands of unstructured documents, combining OCR, vision models, and fine-tuned LLMs to reach ~97% field-level accuracy with structured output schemas. Reduced operational LLM costs by ~70% via token optimization and confidence-based routing that cut human review queues by ~60%, backed by systematic evaluation for extraction accuracy, hallucinations, and output compliance before deployment. Developed adaptive agentic AI for reliable web data extraction using LLM-guided navigation to replace brittle hard-coded scrapers, and authored technical documentation

AI Python Developer at Empiric Infotech LLP

January 20, 2024 - May 31, 2025

Built a full-stack AI chatbot platform using OpenAI APIs, FastAPI, and React with secure authentication (JWT session management) and Mixpanel analytics, deployed via Docker and CI/CD. Engineered a scalable multi-country Amazon scraping tool using Selenium and a Django REST backend, integrated with Airtable/Xano, and automated workflows via n8n. Developed multilingual AI systems including a Quiz AI chatbot with audio prompts, admin CMS, and a responsive frontend, delivering production deployments and API integrations across multiple projects.

Backend Python Developer at Onfess (EasyTech Innovations Pvt Ltd)

June 1, 2021 - December 31, 2023

Developed and maintained Python-based backend services and REST APIs for education ERP modules used by 100+ educational institutions, supporting admissions, fee management, and student record management. Integrated payment gateway solutions and optimized database queries to improve API response times by up to 30%. Collaborated with cross-functional teams to deliver 10+ feature enhancements and resolve critical production issues, improving system reliability and reducing support turnaround time.