We can organize an interview with Aldin or any of our 25,000 available candidates within 48 hours. How would you like to proceed?
Schedule Interview NowMy name is Nikola G. and I have over 1 year of experience in the tech industry. I specialize in the following technologies: AI Implementation, AI Text-to-Image, AI App Development, NLP Tokenization, Deep Learning, etc.. I hold a degree in , Bachelor of Engineering (BEng). Some of the notable projects I've worked on include: Multi-Document RAG with LangGraph, Fully Autonomous AI Agent for Google Drive Document Processing, LLM Fine-tuning, UNet-based edge colorization and cartoonization system, Stateful AI Agent using Langgraph and Azure Cosmos DB, etc.. I am based in Prijepolje, Serbia. I've successfully completed 13 projects while developing at Softaims.
My passion is building solutions that are not only technically sound but also deliver an exceptional user experience (UX). I constantly advocate for user-centered design principles, ensuring that the final product is intuitive, accessible, and solves real user problems effectively. I bridge the gap between technical possibilities and the overall product vision.
Working within the Softaims team, I contribute by bringing a perspective that integrates business goals with technical constraints, resulting in solutions that are both practical and innovative. I have a strong track record of rapidly prototyping and iterating based on feedback to drive optimal solution fit.
I'm committed to contributing to a positive and collaborative team environment, sharing knowledge, and helping colleagues grow their skills, all while pushing the boundaries of what's possible in solution development.
Main technologies
1 year
1 Year
1 Year
1 Year
Potentially possible
Ex:Upwork
Intelligent RAG pipeline for querying multiple financial PDFs with automatic document routing. https://github.com/nikolagojakovic/LangGraph-Agentic-Rag
A solid “fully autonomous” design is an event-driven pipeline: Google Drive change events trigger an orchestrator that plans work, runs document tools (extract/OCR/classify/signature), writes results
This project fine‑tunes the Mistral language model with LoRA adapters on the Dolly 15k instruction dataset to maximize ROUGE‑L performance for text generation tasks. It provides a reproducible trainin
This project is a UNet-based edge colorization and cartoonization system that turns regular photos into stylized, cartoon‑like images. It uses Canny edge detection as an additional input channel to a
This project is an Azure-based stateful travel assistant that uses GPT‑4.1 and Azure Maps to answer route and traffic questions from a client app. The client sends a request to an Agent API, which coo
in
2021-01-01-2025-01-01
Bachelor of Engineering (BEng) in
2025-01-01-2029-01-01