Даніїл

DANIIL OLIINYK
AI Engineer
A I & M L E n g i n e e r w i t h 2 + y e a r s o f c o m m e r c i a l e x p e r i e n c e s p e c i a l i z i n g i n N L P, L L M o r c h e s t r a t i o n , a n d
Predictive Modeling.
P r o v e n t r a c k r e c o r d o f d e v e l o p i n g c o s t - e ff e c t i v e A I s o l u t i o n s ( r e d u c e d i n f r a s t r u c t u r e c o s t s b y u p t o
460x vs cloud providers) and building stateful multi-agent systems using LangGraph.
E x p e r i e n c e d i n e n d - t o - e n d d e p l o y m e n t , f r o m f i n e - t u n i n g o p e n - s o u r c e m o d e l s ( X L M - R O B E RTa ) t o
d e p l o y i n g s c a l a b l e R E S T A P I s o n A z u r e a n d AW S .

C O N TA C T S : L i b e r e c , C z e c h i a ( C u r r e n t l o c a t i o n )
Email: [открыть контакты](см. выше в блоке «контактная информация»)
Te l e g r a m : @ f i d u s _ v a l
L i n k e d l n : h t t p s : / / w w w. l i n k e d i n . c o m / i n / - d a n i i l - o l i i n y k - /
Git hub: https://github.com/Fidus1337

SKILLS
A I & M a c h i n e L e a r n i n g : N L P, P re d i c t i ve M o d e l i n g , M u l t i - A g e n t S y s t e m s , L L M O rc h e s t ra t i o n ,
P ro m p t E n g i n e e r i n g , D a t a S c i e n c e , S t a t i s t i c s .
Fra m e w o r k s & L i b ra r i e s f o r m u l t i a g e n t s y s t e m s : Tra n s f o r m e r s ( H u g g i n g Fa c e ) , L a n g C h a i n ,
L a n g G ra p h , L a n g S m i t h , O p e n A I A P I .
B a c ke n d E n g i n e e r i n g : P y t h o n , Fa s t A P I , R E S T A P I s , Po s t g re S Q L , M y S Q L , D j a n g o
C l o u d & D ev O p s : AW S , A z u re ( C o n t a i n e r I n s t a n c e s , B l o b S to ra g e ) , D o c ke r, C I / C D ( G i t H u b
Actions), Git, Linux.

WORK EXPERIENCE

AI & Machine Learning Engineer | [06, 2025] – Present
"Future Graph” Startup
Multi-Agent Orchestration: Architecting and developing a stateful multi-agent system
using LangChain and LangGraph to automate financial market research and analyze
news sentiment.
Predictive Modeling: Designed and trained predictive machine learning
models to forecast BTCUSDT price direction, achieving 60% accuracy, 60%
precision, and 70% recall through advanced feature engineering.
End-to-End Deployment: Built and deployed scalable
REST APIs using FastAPI, Docker, and AWS to serve
predictive models and agentic workflows.

AI & NLP Engineer | [01, 2024] – [05, 2025]
"PII Removal System" Startup
(GDPR Compliance & Document Anonymization)
DEMO API - https://pii.it-sprout.org.ua/
Custom NLP Pipeline: Developed and fine-tuned a custom Named Entity Recognition
(NER) model based on XLM-ROBERTa. Achieved 97% accuracy across English, Russian,
and Ukrainian languages.
Market-Leading Accuracy: Outperformed out-of-the-box cloud NLP solutions from
AWS, Azure, and Google in accuracy for Slavic languages.
Cost Optimization: Slashed infrastructure costs by 10x to 460x compared to enterprise
cloud NER solutions by heavily optimizing the model for CPU-based inference.
High-Performance Backend: Engineered a REST API using FastAPI capable of
processing and anonymizing 86 document pages (resumes) per minute.
LLM Integration: Implemented automated data quality verification utilizing the OpenAI
API to ensure flawless PII redaction.
Cloud Infrastructure: Managed end-to-end deployment by containerizing the
application with Docker and hosting it on Azure Container Instances alongside Blob
Storage.
Backend / AI Engineer | [01, 2024] – [06, 2024]
AI JobTech Platform
Site for automatizaton of searching job
Backend Development: Architected and developed a FastAPI-based + Django backend
prototype designed to automate the job search process, including resume tailoring and
application outreach.
LLM Integration: Integrated the OpenAI API to dynamically generate personalized
cover letters and adapt resumes based on specific job descriptions and keywords.
Automated Dispatch System: Engineered the core logic and scripts for an automated
email outreach system to send personalized applications to recruiter databases.
Technical Scope: Gained hands-on, from-scratch development experience in
building AI-driven content generation pipelines and orchestrating API
workflows

E D U C AT I O N
Oles Honchar Dnipro National University (DNU)
Bachelor of Applied Mathematics September 2024 — Present (Expected Graduation: 2027)
Currently enrolled in an accelerated 2.5-year Bachelor's program based on my prior college degree.

Machine-Building Professional College of Oles Honchar DNU
Professional Junior Bachelor / Associate Degree in Applied Mathematics September 2020 — June 2024

Languages:
English (B2), Russian (Native), Ukrainian(Native), Czech (B1)