Nikola B.

Key Skills

Software

Other

Scale AI

OpenCV AI Kit (OAK)

Google Cloud Vertex AI

AWS SageMaker

Top Subject Matter

LLM-powered RAG systems evaluation and reliability improvement

NLP semantic search and information extraction model training pipelines

Top Data Types

Text

Document

Audio

Top Task Types

Fine-tuning

Polygon

Cuboid

Evaluation/Rating

Prompt + Response Writing (SFT)

Computer Programming/Coding

Freelancer Overview

Senior AI Engineer, HTEC GROUP (Aug 2023 – Present). Brings 10+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Bachelor’s Degree, University of Belgrade (2017). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and Fine-tuning.

Labeling Experience

Senior AI Engineer, HTEC GROUP (Aug 2023 – Present)

Text

Built and maintained evaluation frameworks for LLM/RAG outputs to iteratively improve answer accuracy and reliability in production. Used continuous prompt tracking and feedback loops to refine model behavior over time. • Conducted ongoing evaluation and refinement of enterprise LLM platform performance. • Reduced hallucinations and improved answer accuracy through iterative testing. • Implemented observability for prompt tracking and feedback collection. • Supported faster iteration speed via structured evaluation workflows.

2023 - Present

AI Engineer, 4 Point O Labs (Feb 2020 – Jul 2023)

OtherTextFine-tuning

Built production-ready NLP systems for semantic search, document understanding, and information extraction using transformer-based text modeling. Designed end-to-end ML pipelines spanning data ingestion, preprocessing, model training, evaluation, and deployment. • Trained and tuned transformer architectures for text-processing tasks. • Implemented end-to-end ML pipeline workflows for NLP extraction models. • Automated model retraining, validation, and monitoring to accelerate experimentation. • Improved model performance and deployment timelines through pipeline optimization.

2020 - 2023

Education

Work History