I work at the intersection of AI engineering, mathematical research, algorithms, and software engineering.
My mathematical background shapes how I approach engineering problems: understand the structure, make assumptions explicit, choose a suitable model or method, implement it carefully, and evaluate what actually happened.
My current direction is AI Engineering with strong mathematical and software-engineering foundations, especially for systems involving retrieval, learning, optimization, adaptation, and decision-making.
| Problem Structure & constraints |
→ | Model Assumptions & representation |
→ | Algorithm / AI Method & implementation |
→ | System Reliable behavior |
→ | Outcome Measure & improve |
|
RAG systems, embeddings, information retrieval, hybrid search, reranking, grounded generation, citation verification, evaluation, and AI-backed services. |
Mathematical modelling, optimization, numerical algorithms, and research-driven learning methods where problem structure informs computation. |
|
Systems that observe execution, learn from evidence, make decisions, adapt behavior, and evaluate the result through explicit feedback loops. |
Architecture, APIs, backend and distributed systems, testing, reliability, reproducibility, experiments, benchmarks, and research implementations. |
|
A research-oriented RAG system focused on evidence retrieval, hybrid search, reranking, grounded generation, citation verification, and measurable evaluation.
|
A research-oriented framework exploring learning-native adaptive software through the loop: observe → learn → decide → adapt → evaluate
|
|
A mathematical optimization implementation focused on convex quadratic programming, numerical reasoning, correctness, and testing.
|
An exploration connecting metaheuristic optimization, event-driven architecture, and reproducible experimentation.
|
|
Primary |
Scholarly Google Scholar |
Technical Community Established identities and research-artifact records are listed here. Pending identity claims are intentionally omitted until independently verified. |
My academic work is grounded in mathematics, with research spanning fixed-point and best-proximity-point theory, fuzzy analysis, differential and integral equations, and related mathematical modelling.
That background is not separate from my engineering work. It influences how I formulate problems, reason about algorithms, investigate learning methods, and turn research ideas into implementations that can be tested and evaluated.
|
Languages C# · Python · TypeScript · JavaScript AI / ML Machine Learning · Deep Learning · LLMs · RAG · Embeddings · Information Retrieval · Optimization |
Backend & systems .NET · ASP.NET Core · APIs · PostgreSQL · Redis · Messaging · Distributed Systems Frontend React · Next.js · Angular · Blazor |
Understand the problem before optimizing the implementation.
I keep the important reasoning visible:
| 01 Define |
→ | 02 Baseline |
→ | 03 Choose |
→ | 04 Test |
→ | 05 Measure |
→ | 06 Analyze |
→ | 07 Improve |
The goal is not simply to make a system work, but to understand why it works, where it fails, and how its behavior can be improved.
Mathematical Reasoning + Machine Learning + AI Systems + Optimization + Software Engineering
I am particularly interested in AI systems that do more than generate output: systems that retrieve evidence, reason over structured information, optimize decisions, learn from feedback, and remain inspectable and reliable.
research · engineering · intelligent systems