
Building software like bridges; strong, reliable and no room for miracles!
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
DuelingDQN
March 22, 2025 – March 22, 2025
This repository contains an implementation of a Dueling Deep Q-Network (Dueling DQN) agent trained to play Atari Pong using RAM state inputs from the `ALE/Pong-ram-v5` environment in Gymnasium. The agent uses Double DQN, experience replay & epsilon-greedy action selection to stabilize learning.
View ProjectNeuralNetworkTrain
March 19, 2025 – March 20, 2025
This repository contains a fully implemented neural network from scratch using NumPy. The model is trained to recognize handwritten digits from a dataset, using forward propagation, backpropagation and gradient descent for optimization.
View ProjectNeuralMachineTranslation
March 15, 2025 – March 15, 2025
Swahili-English Neural Machine Translation using Seq2Seq with LSTM. Trained on parallel corpora, evaluated with BLEU scores and tested for accuracy. Results show moderate BLEU but low exact-match accuracy, highlighting areas for improvement.
View ProjectYOLOv12ObjectDetection
March 1, 2025 – May 26, 2025
YOLOv12 object detection pipeline: Training, evaluation, and inference on custom datasets with TensorBoard visualizations.
View ProjectMaskRCNN
January 31, 2025 – February 1, 2025
Pedestrian Detection using Mask R-CNN : Instance segmentation for identifying pedestrians in images.
View Projectkairo-s_car_rental
January 14, 2025 – January 14, 2025
Optimize car movements between two rental locations using Markov Decision Processes (MDP) and Policy Iteration. Includes cost modeling, Poisson demand simulation and visualization of the optimal policy.
View Projectgamblers_problem
January 12, 2025 – January 12, 2025
Reinforcement Learning implementation of the Gambler's Problem using Value Iteration to find the optimal betting policy.
View Projectk_armed_bandit
January 10, 2025 – August 13, 2025
k-armed-bandit: A Python implementation of the k-armed bandit problem, featuring ε-greedy and gradient bandit algorithms to explore the trade-off between exploration and exploitation in reinforcement learning. Includes visualization and performance comparison tools.
View ProjectLeagueOfRobotRunners-MAPF
April 16, 2024 – May 18, 2024
This repository hosts the MAPF algorithms and simulations for the League of Robot Runners competition. It features implementation of state-of-the-art algorithms for coordinating multiple robots efficiently on predefined maps, ensuring collision-free navigation.
View ProjectCarClassification
May 2, 2023 – January 20, 2025
This repository contains a Jupyter notebook for a Convolutional Neural Network (CNN) implemented in PyTorch to classify images of cars.
View ProjectCultural Fit Analysis
The candidate's projects are exclusively personal and heavily focused on academic/research-oriented machine learning implementations. While demonstrating strong technical curiosity and initiative, there is no evidence of experience in collaborative team environments, production-level systems, or diverse project types that might indicate broader cultural adaptability. The lack of professional experience or team projects suggests a potential gap in understanding real-world software development lifecycles and team dynamics, which could impact cultural fit in a product-focused role.
Soft Skills & Operational Fit
Insufficient data to assess soft skills or operational fit. The candidate's project descriptions indicate a strong technical focus and ability to execute complex algorithms, but provide no insight into collaboration, communication, or problem-solving approaches in a team setting.