CV

Profile

Selected publications

1. Igor Bogdanov, C. Huang. “Discovering Cross-Language Reasoning Invariance in LLMs with Geometry-Invariant Sparse Autoencoders.” ICML 2026 Workshop on Mechanistic Interpretability.
2. Igor Bogdanov, C.-H. Lung, T. Kunz, J. Gao, A. Taylor, M. Zaman. “Context, Reasoning, and Hierarchy: A Cost–Performance Study of Compound LLM Agent Design in an Adversarial POMDP.” ACM Conference on AI and Agentic Systems (CAIS), 2026. DOI: 10.1145/3786335.3813149
3. Igor Bogdanov, C.-H. Lung, T. Kunz, J. Gao, A. Taylor, M. Zaman. “FORGE: Self-Evolving Agent Memory With No Weight Updates via Population Broadcast.” ACM Conference on AI and Agentic Systems (CAIS), 2026. DOI: 10.1145/3786335.3813155
4. Igor Bogdanov, O. Manakina, C.-H. Lung. “Evaluation of Multi-Turn Consistency in LLM Agents: Survival Analysis and Failure-Rationale Taxonomy.” ICLR 2026 Workshop on LLM Logical Reasoning.
5. O. Manakina, Igor Bogdanov, C.-H. Lung. “Delay-of-Gratification as a Multi-Agent Survival Micro-Benchmark for Long-Horizon LLMs: Social Exposure, Personas, and Tool Use Budgets.” NeurIPS 2025 Workshop on Multi-Turn Interactions in Large Language Models.
6. O. Manakina, Igor Bogdanov. “Learning to Grade Efficiently: A Bandit-Driven Prompt-Selection Framework for Low-Cost LLM Essay Scoring.” EDM 2025 Workshop on Leveraging LLMs for Innovative Educational Data Mining (WLIEDM).
7. Igor Bogdanov, J. Green. “Infant Care Video Dataset for Classification of Interventions Using Transformers.” IEEE COMPSAC 2025, MediComp Symposium. DOI: 10.1109/COMPSAC65507.2025.00299

Invited talks and presentations

• Invited research poster presentation, AI Engineer World’s Fair 2026, Research Papers track, San Francisco, June 29 – July 3, 2026: “Compound LLM agent design and FORGE: prompt-only memory evolution.”
• Short talk, Montreal Child CDSS Congress (M3C), Montreal, May 2024: “Video-Based Clinical Intervention Detection and Classification with Summary Report Generation Using Transformer Models.”

Experience

• Graduate AI Researcher, Carleton UniversityMay 2024 – May 2026

  Realistic and generalizable training of autonomous cyber agents. Designed and implemented compound LLM-agent systems for decision-making in complex, stochastic, partially observable environments. Built the experiment infrastructure.

• Founder & Technical Director (part-time), Appalect2018 – present

  Architecture and hands-on development across web, mobile, backend, automation, and integration systems, from concept and prototyping through deployment and iteration.

• Teaching Assistant, Carleton UniversityMay 2023 – present

  Intro to Machine Learning (designed assignments and the course project, weekly hands-on AI/ML/DL tutorials for 120+ students), Computer Systems Lab, Real-Time Concurrent Systems, and Intro to Python.

• Founder & CTO, IBCICO Development2009 – 2017

  Founded and led a full-cycle software development agency, managing an engineering team through the entire software development life cycle building financial data systems, e-commerce, and ticket-booking platforms.

Education

• Master of Applied Science (MASc), Electrical and Computer Engineering2024 – 2026

  Carleton University · CGPA 11.6/12.0 (GPA 4.0/4.0)

  Thesis: Design and Gradient-Free Adaptation of Compound LLM Agents in a Partially Observable Adversarial Networked Environment

• Bachelor of Engineering (B.Eng.), Computer Systems Engineering · minors in Mathematics and Physics2019 – 2024

  Carleton University · High Distinction, CGPA 10.78/12.0

• Specialist Diploma (five-year), Linguistics and Intercultural Communication2000 – 2005

  Moscow State Regional University · Cumulative GPA 4.7/5

Technical skills

Languages, storage, and AI/ML frameworks

Python, C/C++, Java, JavaScript, Verilog, SystemVerilog, Swift, Objective-C, Ruby; PyTorch, JAX, TensorFlow, Hugging Face, NumPy, scikit-learn, Pandas, LangChain; OpenAI, Anthropic, and Gemini APIs; CUDA/GPU; FAISS and RAG; SQL, MySQL, PostgreSQL, MongoDB, Firebase, SQLite, Redis, DuckDB.

ML, post-training, and adaptation

Transformers, CNNs, GNNs, RNNs; RL (PPO, DPO, GRPO); LoRA, SFT; prompt engineering; in-context and continual learning.

AI systems, CI/CD, and infrastructure

Multi-agent orchestration; GPU/cloud; Bash, Linux/Unix, Make, Git, GitHub Actions, Docker, LXD; FPGA prototyping; GPU and network optimization; Ethernet, AXI4, PCIe, TCP/IP.