Jide Oyelayo
CV

Working paper · Revised 17 Nov 2026

Jide Oyelayo

Software engineer building search and retrieval systems in C++, Python and C#, across performance engineering, ML retrieval and quantitative systems.0

CVEmailLinkedIn GitHub

1 Selected work

1 of 4 flagships · 6 of 14 archive entries

1.4 Poker engine and self-play agents Draft

Role Author/Stack C++20, Python, PyTorch, pybind11/Date Jan 2026/Track ML, Quant

Problem. Learn to play a simplified multi-player Texas hold’em by self-play alone, with no poker knowledge given to the agents, and check what they learn.

Method. A C++20 game engine bound to Python with pybind11; Deep Q-Network agents (MLP, LSTM, GRU and Transformer) trained by self-play with legal-action masking and a terminal reward in big blinds; evaluation against fixed baseline bots on duplicate deals; symbolic regression to summarise how they value starting hands.

Result. No trained agent beats a fixed baseline reliably: against the random and calling bots every 95% interval over 3 seeds contains zero, and every agent loses to a tight bot (2,000 training hands per seed)

Read the case study

Fig. 1.4 Pocket-hand expected value Mean expected value in big blinds per hand for each starting hand after 100,000 self-play hands, from images/expected_value_of_pocketcards_100000_iter.png in the repository. Reported in the repository; not re-run here. The logging behind it dropped folded hands and the blinds.
Table 1. Archive: the 6 of 14 projects tagged ML. tbc marks a year still to be confirmed; the CVs or the commit history give years for 6 of these 6.
YearProjectTrackBuilt withLinks
2024Orderbook Simulation Order matching and VWAP in C++, a from-scratch neural network for price prediction, Python GUIs.Quant · MLC++, PythonCode
2024C++ Machine Learning Library Common machine-learning algorithms implemented as a C++ library. In progress.ML · SystemsC++Code
2022Neural Network Electronics Simulation A from-scratch neural network that models XOR, NAND, MUX, DEMUX, adder and flip-flop circuits.ML · SystemsC++Code
2022Four In A Row AI Four-in-a-row opponent using minimax search with alpha–beta pruning.MLC++Code
2022Flask Rowing App Logs rowing splits and predicts average speed from past sessions.ML · SoftwarePython, Flask
2023Low-Cost Smart Agricultural Sensing System Soil sensing for small-scale rice farmers in South Asia, with a decision tree and a companion app.Embedded · MLArduino, MATLAB, React Native, REST APIsCodeApp code

2 Experience

  1. Apr 2026 – PresentSoftware Engineer, Logos ResearchOwn and optimise the search service across more than 400,000 indexed items, using Python and C# to deliver fast, reliable retrieval at platform scale.
  2. Aug 2025 – Sep 2025Freelance Software Engineer, Great Child NurseryBuilt the nursery website in React and TypeScript on Firebase, with client-side caching to cut database calls.
  3. Jan 2024 – Jun 2025Junior Software Developer, Carbon & FinchDeveloped and optimised SQL jobs that analysed large volumes of sales-order data.
  4. Jun 2022 – Sep 2022Junior Software Engineer, IDEX BiometricsDeveloped a MATLAB client for analysing fingerprint-sensing biometric systems.
  5. Jun 2021 – May 2022Technical Director, Engineers Without Borders University of WarwickAutomated society operations with UiPath and C#, saving more than three hours each week.

3 Notes

Maturity scale:draftworkingfinished

  1. Put–call parity as a unit test

    Using a no-arbitrage identity to catch bugs in an option pricer.

    draftCertainty: certain (it is an identity)Quant

4 Lab

Original games and small demos, each with a line on what it demonstrates. Optional reading.

Enter the Lab
  • Arcade: Snake, Block Stacker, Space Raiders, Coding NinjaProductionGame loops, collision and state transitions, with start, pause and restart in every game.
  • Order book demoLive demoThe C++ order book compiled to WebAssembly: place and cancel orders and watch them match, in the browser.

5 About and proof

I work across backend systems, search infrastructure, performance-focused development and quantitative finance projects. I trained as an electrical and electronic engineer at Warwick, which is where FPGAs and microcontrollers taught me to count cycles. Away from a keyboard: basketball, cycling, and more home automation than strictly necessary.

Working set: Algorithms, Bash, C, C#, C++, CSS3, Electronics, Finance, FPGA, Git, GitHub, JavaScript, Machine Learning, MATLAB, MySQL, Python, Quantitative Analysis, React, Software Engineering, SQL, STM32, SystemVerilog, Terminal, Verilog, VHDL, Visual Studio Code

Degree
MEng Electrical and Electronic Engineering, University of Warwick · 2019–2024 · 2:1
A levels
A* Mathematics, A* Further Mathematics · with Chemistry and Physics (A, A) · Brampton Manor Academy, 2019
Certificates
Financial Derivatives: A Quantitative Finance View; Python for Finance: Investment Fundamentals & Data Analytics; Machine Learning A-Z: AI, Python; C++ Programming from Beginner to Advance 2024 Edition · Udemy, 2024 · CV

Footnotes

  1. Engineers count from zero, so these footnotes do too. This one isn’t a citation; it is a side door to the Lab, where the games live. Enter the Lab → ↩