Mikhail Gorelkin

Framingham, MA, USA | Email: mikhail@gorelkin.com

Principal AI Systems Architect, Principal AI Scientist, and Independent Researcher with 21 years of experience transforming complex, ill-defined business problems into production-grade engineering solutions for global enterprises and early-stage startups. I work end-to-end in AI: from figuring out the right business problem, through architecture for production, to the engineering work itself. Original cross-disciplinary research is the source of competitive advantage I bring — not a separate activity from delivery.

• AI Systems Design & Architecture
• Generative AI / LLMs, RAG systems, LLM-Algorithm Integration, LLM Reliability, Agentic AI
• Artificial Intelligence, Natural Language Processing, Machine Learning, Deep Learning, Graph Neural Networks, Reinforcement Learning, Probabilistic Programming, Automated Decision Making
• Data Science, Forecasting, Optimization, Recommender Systems
• Complex Systems / Multi-Agent Modeling, Cybernetics / Intelligent Adaptive Systems
• Mathematical Modeling, Computer Science Algorithms
• Languages: Python, C++, C#, Scala, Julia, SQL | Core Gen-AI & Agents: Hugging Face, LLMs, Agent Development Kit (ADK), AutoGen, crewAI, LangChain, Agent2Agent (A2A) and MCP protocols, Faiss, Pinecone | Clouds: Google Cloud / Vertex AI, Amazon SageMaker, Amazon EC2 / Linux | Other Tools: PyTorch, TensorFlow / Keras, scikit-learn, spaCy, PySpark, Akka, Mesa, Pyro, PyMC.

• Superintelligence from Complexity, Apr 2026
• The Root Problem of LLM Hallucinations on the Turing Machine, Apr 2026
• Category Theory as a Language for Understanding Large Language Models (LLMs), Mar 2026
• A Categorical X-Ray for Complex Agentic Systems, Feb 2026
• A Complete AI-Driven Architecture for Enterprise Agentic Systems, Jan 2026
• Why Today’s “Agentic AI” Isn’t Truly AI (and How We Can Fix It), Aug 2025

• Cognitively-Augmented Specification Design (CASD): A methodology for complex problems.
• The Bidirectional Semantic Bridge: A configurable neuro-symbolic fusion architecture for LLM-algorithm systems, enabling integration from single-pass to compositional pattern algebra.
• Intelligence Fusion + Cognitive Augmentation: A framework that transforms data into multi-lens interpretations, guiding decision-makers through complexity to solutions aligned with their intuition.

Gorelkin AI Consulting & Advisory,  Boston, MA 04.2005 – Present
Principal AI Systems Architect, Principal AI Scientist, and Independent Researcher | Mathematician

• My customer list includes: Visa, Ford, ServiceNow, Deloitte, Boston Consulting Group, Fractal Analytics, IEEE, Scientific Systems Company, AES, Celsius, airSlate, ADΣXT, NOHOLD, Boston Biotech Clinical Research.
• Cognitive consulting for complex business problems in the AI era: specializing in problems where the bottleneck isn't compute or talent, but the structure and bandwidth of human thought required to specify the right solution.

FieldGoal,  Los Angeles, CA 09.2025 – 02.2026
Principal AI Systems Architect

• Designed an AI approach to agentic systems and an AI‑driven enterprise agentic architecture for the company’s platform, including a cognitively augmented decision layer that replaces traditional reports and dashboards.

Simply Adaptive, London, United Kingdom 01.2010 – 07.2010
Interim Director

• Co-developed strategic consulting frameworks in intelligent adaptive systems for financial institutions.

Compuware Corp., Technology Department, Detroit, MI 03.2000 – 11.2004
Software Developer VII

• Researched and developed many advanced features for QALoad (automated performance and scalability testing software), which allowed the company to acquire several big clients like Bank of America from competitors. Prepared a paper for publication on discovering server scalability bottlenecks based on the Kruskal-Wallis test and modified Hodges-Lehmann estimators for statistical modeling.

Central Transport, Sterling Heights, MI 08.1996 – 02.2000
Systems Architect

• Managed a team of ten engineers to develop an NT-based distributed enterprise architecture for terminals across the US, Canada, and Mexico.

Voronezh State University,Voronezh, Russia
Master of Science, Mathematics

• Focused on Topological Methods in Nonlinear Functional Analysis.

• MCP: Build Rich-Context AI Apps with Anthropic, Anthropic, 2025
• Multi AI Agent Systems with crewAI, Parts 1 & 2, crewAI, 2025
• AI Agentic Design Patterns with AutoGen, Microsoft & Penn State University, 2024
• Retrieval Augmented Generation (RAG), Coursera / DeepLearning.AI, 2025
• Train & Fine-Tune LLMs for Production, Intel, 2023
• Machine Learning in Production, Coursera / DeepLearning.AI, 2025
• Quantum Computation using Qiskit, IBM, 2022
• Quantum Computing, Coursera / Saint Petersburg State University, 2021
• Algorithmic Information Dynamics, Santa Fe Institute, 2018
• Parallel Programming in Scala, Coursera / École Polytechnique Fédérale de Lausanne, 2017
• Text Mining and Analytics, Coursera / University of Illinois at Urbana-Champaign, 2015
• Statistical Learning, Stanford University, 2014
• Mining Massive Datasets, Coursera / Stanford University, 2014
• Introduction to Dynamical Systems and Chaos, Santa Fe Institute, 2014
• Introduction to Complexity, Santa Fe Institute, 2013
• Game Theory, Coursera / Stanford University, 2013
• Natural Language Processing, Coursera / Columbia University, 2013
• Algorithms: Design and Analysis. Parts 1 & 2, Coursera / Stanford University, 2013
• Machine Learning, Coursera / Stanford University, 2012
• Model Thinking, Coursera / University of Michigan - Ann Arbor, 2012

• Categories for AI, DeepMind, 2023
• Introduction to Quantum Computing & Quantum Machine Learning, IBM, 2022
• Introduction to Agent-Based Modeling, Santa Fe Institute, 2020
• Bayesian Methods for Machine Learning, Coursera / National Research University Higher School of Economics, 2019
• Deep Natural Language Processing, University of Oxford & Google DeepMind, 2017
• Deep Learning (TensorFlow), Udacity / Google, 2016
• Approximation Algorithms. Parts 1 & 2, Coursera / École Normale Supérieure, 2016
• Functional Programming Principles in Scala, Coursera / École Polytechnique Fédérale de Lausanne, 2015
• Deep Learning for Natural Language Processing, Stanford University, 2015
• Neural Networks for Machine Learning, Coursera / University of Toronto, 2015
• Machine Learning: Reinforcement Learning, Udacity / Georgia Tech, 2014

• The Conference on Neural Information Processing Systems, 2020
• The International Conference on Probabilistic Programming, 2018
• O'Reilly Artificial Intelligence Conference, 2016-2018
• IEEE International Conference on Self-Adaptive and Self-Organizing Systems (SASO), 2007