Halil – LLM, RAG, LangChain

A UK-based technology studio specializing in AI/ML systems and custom web and mobile application development.

• Founded the studio to deliver AI-driven software solutions focused on LLMs, agentic systems, and scalable microservice architectures.
• Built production-grade systems including FastAPI services, multi-agent orchestration with LangGraph, and data-driven automation pipelines.
• Worked with clients on an Outside IR35 basis across AI, cloud, and back-end engineering.

ProWry is an AI-powered grant-writing assistant purpose-built for the funding ecosystem. It helps applicants draft, analyse, and strengthen grant applications by combining a multi-agent LLM pipeline with domain-specific evaluation logic. I designed and built the product end-to-end — from the agentic backend and retrieval layer to billing and the freemium go-to-market — and shipped it as a live SaaS.

• Designed and built the entire stack using FastAPI, Redis, Supabase, Stripe, and custom multi-agent orchestration with LangChain and LangGraph.
• Implemented a 5-step AI analysis engine that evaluated grant applications across multiple dimensions and produced actionable improvement recommendations.
• Built a retrieval-augmented (RAG) layer over a vector database to ground recommendations in relevant funding context and reduce hallucinations.
• Launched a PLG freemium model with a Pro tier for serious applicants.
• Cut grant-application preparation time by roughly 10x from days of manual drafting to under an hour.

An end-to-end SLA reporting for the client.

• Architected and deployed production-grade RESTful APIs using FastAPI, delivering full CRUD functionality for SLA rule trees, metadata queries, and automated report generation.
• Built enterprise-ready Python modules for SLA logic parsing and SQL generation with Pydantic-enforced schema validation, ensuring type safety and reducing runtime errors.
• Engineered a scalable plugin-based microservices architecture, enabling modular feature deployment and reducing system coupling.

A conversational AI chatbot for the company's sales teams, designed to increase sales and optimize customer-product matching.

• Developed an advanced chatbot using the LangChain framework to improve customer service interactions and operational efficiency.
• Built a customer profiling tool using ML algorithms including XGBoost, Random Forest, KNN, and Naive Bayes, and Apriori for identifying potential customers and enhancing marketing strategies.
• Specialized in Explainable AI to promote transparency and trust in AI-driven decisions.
• Deployed robust and scalable AI applications using Django and FastAPI.
• Created test automation scripts for web portals using Selenium and Jenkins, significantly reducing manual testing efforts and improving accuracy.
• Extracted, wrote, and performed consistency checks with Oracle databases.
• Utilized GCP and AWS to deploy scalable AI solutions, ensuring high availability and performance.

A company that builds digital and ICT solutions, with a focus on innovation, software, and new telecom technologies.

• Developed a virtual background feature for the application using CNN and computer vision techniques.
• Created a crawler to detect and highlight key terms in legal documents for the legal team using NLP.
• Developed a tool to read subscriber contracts via OCR and store extracted data in a database.
• Built a script to monitor the network performance of applications.
• Developed a Python-based tool to connect with backend nodes and extract reports for system optimization.

A company that builds digital and ICT solutions, with a focus on innovation, software, and new telecom technologies.

• Performed CNO optimization and automation.
• Used AWS cloud computing and DevOps tools including Ansible, Jenkins, Docker, and Kubernetes.
• Developed programming and scripting solutions with Python.
• Supervised CS and PS services with strong focus on QoS, QoE, and subscriber behavior understanding.
• Analyzed 2G, 3G, and 4G network end-to-end performance and investigated root causes of performance degradations.
• Applied mobile development and testing knowledge using Selenium and Appium.
• Analyzed network KPIs and KQIs from a business perspective.