# Myron Sukhanov Research Engineer · LLM post-training & evaluation · Scientific ML Passionate research engineer with experience in LLM post-training and evaluation, scientific ML, and distributed training on HPC. Cambridge, UK - [Email](mailto:myron.sukhanov@gmail.com) - [GitHub](https://github.com/myrsu) - [LinkedIn](https://www.linkedin.com/in/myron-sukhanov/) ## Currently - Visiting Researcher, Applied ML, University of Cambridge, since Sep 2023 - First-author paper, manuscript in preparation, LLM distillation, 2026 ## Research ### Molecule-Agnostic ML Nanocavity Separator University of Cambridge · manuscript in preparation (2026) - Co-designed, built, and trained a molecule-agnostic ML system for single-molecule SERS spectroscopy data, achieving AUROC 0.97 on human-labelled scans of an unseen molecule - Achieved +5.3 dB PSNR compared to the previous-best model within the Physics for Sustainable Chemistry and NanoPhotonics groups ### Benchmark Gains Without Reasoning Gains: Filtering, Labelling and Weighting Verified Traces for Distillation First author · manuscript in preparation (2026) **Abstract:** We compare methods of leveraging a dataset of chain-of-thought (CoT) traces, where an LLM is prompted to come up with novel and/or groundbreaking heuristics for NP-hard problems. Each of the traces was prompted to end with an executable algorithm that is scored by performance and checked for feasibility by a deterministic verifier. We try three ways of distilling knowledge: *gate*, *grade*, and *weight*. The gate keeps only CoTs that lead to valid algorithms, the grade fine-tunes on all the traces but assigns a quality label to each, and the weight scales the training loss of each trace based on the performance of the algorithm. We find that the gate is the most promising statistically significant recipe among those tested, scoring a 3.0pp accuracy gain on GSM8K against the unlabelled pool and beating the base by 8.0pp. However, when we investigate further, we find that benchmark improvements over the base come from an increased answer emission rate. When comparing the models' performance on answered-only tests, we find that the base beats all fine-tuned models and beats the gate by 8.6pp. This is a signal that problem-specific fine-tuning of already heavily post-trained 4B–8B-parameter models may get an enhanced emission rate at most. ### LLMxLaw Hackathon King’s College, University of Cambridge · Jun 2024 - Developed a solution proposed by Google Cloud: Retrieval Augmented Generation (RAG) based LLM solution to help lawyers find critical points within contract negotiation using Vertex AI API and Streamlit ## Experience ### University of Cambridge **Visiting Researcher, Applied ML (part-time)** · Sep 2023 – Present · Cambridge, UK - Co-designed and built a molecule-agnostic ML system for SERS spectroscopy data - Co-developed [Scanalyser](https://github.com/nanophotonics/scanalyser) — a library and scripts for ML model training and inference on an HPC cluster **Research Intern, Applied ML** · Jun 2023 – Sep 2023 · Cambridge, UK - Reduced the model’s training and inference time by at least 10x via hyperparameter tuning and changing the architecture without performance loss - Implemented distributed training on the GPU cluster via a custom training loop leveraging computational-graph optimisations ### The Innovation Game **Computational Scientist (part-time)** · Aug 2024 – Jun 2025 · Cambridge, UK - Researched reinforcement learning (RL) on chain-of-thought (CoT) for self-improving reasoning agents - Conducted theoretical AI research for the Neural Network Gradient Descent challenge, which rewards researchers for breakthrough optimisers. See the [technical paper](https://docs.tig.foundation/static/neural-network-optimizer.pdf) ### Extreme Light Infrastructure, ELI Beamlines **Research Intern, Data Analysis** · Jul 2022 – Aug 2022 · Prague, Czech Republic - Ran HPC simulations and Fourier analysis of coherent radiation spectra. [More on GitHub](https://github.com/myrsu/PythonSimulations) - Contributed data to the [Physical Review Research paper](https://journals.aps.org/prresearch/abstract/10.1103/PhysRevResearch.6.L032013) on relativistic interactions ## Education ### University of Sheffield **BSc Computer Science (Artificial Intelligence), full scholarship** · Sep 2023 – Jun 2026 · Sheffield, UK - Grade: First Class Honours - Dissertation: Enhancing Reasoning in Language Models via Verified Algorithmic Chain-of-Thought Distillation - Supervisor: Prof. Nikos Aletras ### Taras Shevchenko National University of Kyiv **BSc Physics (discontinued), grade 93%** · Sep 2020 – May 2022 · Kyiv, Ukraine ### Certifications - [Deep Learning specialization, DeepLearning.AI](https://www.coursera.org/account/accomplishments/certificate/4J2HYYM7VQBU) - [Machine Learning, Stanford University](https://www.coursera.org/account/accomplishments/certificate/TDXGV6T77AQD) ## Awards - Mar 2017: 17th nationwide, Ukrainian Physics Olympiad - Mar 2018: 35th nationwide, Ukrainian Physics Olympiad - Feb 2018: 3rd diploma, Ukrainian Programming Olympiad Regional stage - Oct 2018: 2nd diploma, Ukrainian Programming Olympiad City stage - 2016–2019: 1st overall in Kherson City, Ukrainian Physics Olympiad City Stage (4 consecutive years) ## Contact [myron.sukhanov@gmail.com](mailto:myron.sukhanov@gmail.com) · [GitHub](https://github.com/myrsu) · [LinkedIn](https://www.linkedin.com/in/myron-sukhanov/) --- © 2026 Myron Sukhanov · [Privacy](https://myronsukhanov.com/privacy/) · Web version: https://myronsukhanov.com/