Open to opportunities

Nikola Blagojevic

@nikolablagojevic

Message

Senior AI Engineer specializing in LLM-powered RAG and multi-agent systems, delivering scalable, production-grade AI.

Serbia

Message

What I'm looking for

I’m looking to build production-grade LLM/RAG and multi-agent systems on cloud-native infrastructure—where evaluation, observability, and performance optimization are non-negotiable, and mentorship and architecture ownership are valued.

I’m a Senior AI Engineer with 8+ years of experience designing, building, and deploying scalable AI/ML systems and distributed applications. I specialize in LLM-powered platforms, Retrieval-Augmented Generation (RAG), and multi-agent architectures, translating cutting-edge approaches into production-ready impact.

At HTEC GROUP, I architected and led enterprise-scale LLM platforms and advanced RAG systems with Python (FastAPI), supporting 80K+ active users while improving answer accuracy by 45%+ and reducing hallucinations by 30%. I also built multi-agent workflows that cut manual workload by 35%, reduced latency by 40%, and achieved 99.9% uptime on Kubernetes (AWS EKS)—backed by evaluation, observability, and continuous refinement.

Experience

Work history, roles, and key accomplishments

Current

Senior AI Engineer

Current

HTEC Group

Aug 2023 - Present (2 years 9 months)

Architected and led enterprise LLM and advanced RAG platforms that supported 80K+ active users, improving answer accuracy by 45%+ and reducing hallucinations by 30%. Reduced inference latency 40% and infrastructure costs 25% by building async, batching, caching, and streaming pipelines and deploying AI microservices on Kubernetes (AWS EKS) with 99.9% uptime.

LLM RAG fastAPI Vector Search Multi Agent Systems Kubernetes Prompt Evaluation Observability

AI Engineer

4 Point O Labs

Feb 2020 - Jul 2023 (3 years 5 months)

Built production-ready NLP systems for semantic search, document understanding, and information extraction, improving search relevance and accuracy by 35%. Developed real-time AI services with FastAPI and WebSockets handling 10K+ daily requests and reduced deployment time 40% by delivering end-to-end ML pipelines.

NLP Semantic Search fastAPI WebSockets PyTorch TensorFlow Machine Learning Pipelines Transformer Tuning Model Monitoring

Machine Learning Engineer

Nine Pixels

Oct 2017 - Nov 2019 (2 years 1 month)

Created recommendation systems and predictive models that increased user engagement 25–40% and improved conversion rates. Built scalable data processing pipelines for terabyte-scale datasets, reducing processing time by 50%, and deployed ML models as microservices to improve modularity and reduce integration time 30%.