Building AI-powered systems that solve real-world problems.
An Applied AI Engineer building intelligent applications, AI-powered automation systems, and reliable backend solutions. I work with Python, LLM integrations, agentic workflows, API development, and structured validation to transform complex problems into practical software solutions. With an additional interest in cybersecurity, I focus on building systems that are not only intelligent but also reliable, secure, and maintainable.
Building intelligent systems
that solve real-world problems.
I'm Dhruv Dobariya, an Applied AI Engineer passionate about building intelligent software systems that solve real-world problems. My work focuses on AI-powered automation, Large Language Model (LLM) integration, backend engineering, and developing practical applications that connect AI capabilities with real business needs.
Currently working as an AI Engineer Intern at Kombee Technologies, I develop AI-assisted workflows using Python, OpenAI APIs, Ollama, prompt engineering, and REST API integrations. Alongside AI engineering, I have experience in full-stack development and application security, with a growing interest in combining AI and cybersecurity to build reliable, secure, and intelligent systems.
Human first, model second
AI should extend human capabilities, simplify complex tasks, and solve meaningful problems. Technology is valuable when it creates practical impact for people.
Reliability over guesswork
AI systems need more than intelligent outputs. Proper validation, structured workflows, security, and error handling turn unpredictable model responses into dependable software.
Performance is respect
Efficient software respects people's time. I value clean architecture, optimized workflows, responsive applications, and maintainable engineering solutions.
Designing scalable software for production environments.
Role
Lead AI Engineer
Timeline
12 Weeks (Q1 2026)
Technologies
Python, LangGraph, Qdrant, Claude 3.5 Sonnet, AWS ECS
The Context
Enterprise workflows were heavily dependent on manual data entry and unstructured review steps, creating a 12-hour turnaround bottleneck. Automated scripts failed to handle variance in document formats and unstructured inputs.
The Challenge
Parsing unstructured data tables and files into strict schema formats. Standard retrieval-augmented generation suffered from context leakage and output hallucination loops, causing errors in downstream production databases.
Manual Audit Review
Unstructured tables, emails, and invoices create human bottlenecks with high turnaround times and variance errors.
Execution Profile
Manual Document Audit
Autonomous State Machine
AI Engineer
Kombee TechnologiesBachelor of Science
Uka Tarsadia University · Bardoli , Gujarat, IndiaSpecialization in software engineering.
Bachelor of Science in Information Technology (B.Sc. IT)
Uka Tarsadia University · Bardoli, Gujarat, IndiaCompleted a Bachelor of Science in Information Technology from Uka Tarsadia University with a CGPA of 8.49/10. Developed a foundation in programming, software development, databases, computer science fundamentals, and emerging technologies, with a strong interest in Artificial Intelligence, Machine Learning, and practical software engineering.
How I design and build production systems.
A live simulation of the complete request lifecycle—from query ingestion to production processing and delivery.
Let's build software
that solves real problems.
Whether you are looking to design robust backend architectures, scale query systems, or integrate intelligence into high-touch interfaces, I'm always open to talking design and implementation.