AI Tutor Product @ Llamba Collaboration (Capstone Project)

Role Overview :

What I worked on

• Contributed to a capstone project building an AI tutor to support students in Kenya, where access to learning resources can be limited.

• Helped design and develop the core LLM chatbot pipeline that answers general learning questions through conversational interaction.

• Integrated model calls and response handling to make the system stable and usable for real user queries.

• Worked on implementing Retrieval-Augmented Generation (RAG) so the chatbot can retrieve textbook content and generate grounded responses.

• Supported extending the system to answer organization specific queries by connecting the chatbot to curated knowledge sources.

Impact Highlights:

• Enabled the chatbot to provide useful responses to both general learning questions and subject-focused queries

• Improved response accuracy by grounding answers in retrieved educational material rather than relying only on model memory

• Helped move the system toward a learning assistant designed for real classroom usage

• Contributed to a project focused on practical educational impact.

Tech Stack:

Python, Flask, React, Node.js, LLaMA, FAISS, Pinecone, ChromaDB, GitHub, Linux

 Growth & Takeaways:

•  Learned how to design LLM systems with real users and constraints in mind.

• Gained deeper experience building chatbot pipelines from input handling to response generation.

• Improved understanding of how retrieval improves factual correctness in generative systems.

• Saw firsthand how AI engineering can be applied to meaningful social impact scenarios.

Machine Leaning Engineer Intern  @ Vosyn AI 

Role Overview :

What I worked on

• Fine-tuned an 8B language model for multilingual translation using QLoRA and multi-GPU training

• Built parts of a translation pipeline deployed on Vertex AI, Cloud Run, and GKE

• Improved model outputs using preference optimization and evaluation methods

• Helped develop a speech-to-speech translation API using Node.js, Django, Docker, and gRPC

Impact Highlights:

• BLEU improvement: 0.00 → 16.06 (JA→EN), 3.08 → 34.56 (AR→EN).

• BLEURT boost: +36%.

• Pipeline latency reduced from 2 minutes → 30–40  (70%) seconds for 25-block SRT files.

Tech Stack:

DeepSeek 8B, LoRA, QLoRA, 8-bit quantization,  DPO,  LLM as a Judge, PyTorch, Hugging Face, Vertex AI, GKE, Cloud Run, Cloud Storage, Docker, GitHub Actions, Python,  Node JS, Django, CUDA, GCP.

 Growth & Takeaways:

• Learned how large language models are trained and tuned across multiple GPUs

• Gained hands-on experience deploying models in real cloud pipelines

• Understood practical latency and scaling challenges in inference systems

• Improved my ability to connect model performance with system design decisions

• Built confidence working across ML, backend, and infrastructure components

Instructor Assistant Upward Bound  @ CU boulder

Role Overview:

• Supporting a programming fundamentals course with 15+ students.

• Assisting lab sessions on Python, covering core topics like:

  • Data types, control flow, and function design

  • File I/O operations

  • Debugging strategies and exception handling

• Providing personalised assistance via Jupyter Notebooks and live feedback during labs.

• Tracking student progress through performance metrics, surveys, and assignment reviews.

Impact Highlights:

• Increased student comprehension by 40% via personalised guidance and iterative feedback.

• Helped multiple students move from basic to intermediate proficiency in Python within one semester.

Tech Stack:

Python, Terminal, VSCode,  Excel,  Google Classroom.

Growth & Takeaways:

• Improved ability to explain abstract programming concepts through analogies and live examples.

• Learned how to tailor technical communication to varied learning styles and skill levels.

Machine Leaning Research Intern  @ DRDO INMAS

Role Overview:

• Designed and implemented a real-time video acquisition pipeline using:

  • Arduino UNO for hardware trigger generation

  • OpenCV and Python for real-time video capture and frame processing

• Achieved hardware-software synchronisation through serial communication and multithreaded signal handling.

• Applied advanced computer vision techniques:

  • Gaussian blur, adaptive thresholding, contour detection

  • Region of Interest (ROI) segmentation for feature extraction

• Enhanced the visual analytics pipeline for researchers performing object-based study of frames in lab settings.

Impact Highlights:

• Latency improvement: 73% faster retrieval.

• Robustified experimental imaging pipelines for extended-duration trials

Tech Stack:

Arduino, OpenCV, Python, Serial Protocols, Multithreading, USB Camera Interface, NumPy, Matplotlib, CNN.

Growth & Takeaways:

• Developed real-time embedded-vision system skills

• Learned performance tuning and multithreaded control at the edge device level

Machine Leaning Research Intern  @ DRDO INMAS 

Role Overview:

• Built CNN models using TensorFlow and Keras to detect COVID-19 from chest X-ray images.

• Preprocessed 700+ real medical images using:

  • noise filtering

  • Data augmentation (flips, rotations, scaling)

• Designed both binary and multi-class pipelines to analyze diagnostic trade-offs.

• Tuned hyperparameters using early stopping, dropout, and L2 regularization to avoid overfitting.

• Generated heatmaps for model interpretability, aiding physician validation of predictions.

Impact Highlights:

• Binary model achieved 93.75% accuracy vs. 71% for multi-class

• Produced visual activation maps for clinical feedback and explainability

Tech Stack:

TensorFlow, Keras, Python, Scikit-learn, Matplotlib, Grad-CAM, NumPy, OpenCV, Jupyter

Growth & Takeaways:

• Strengthened understanding of medical AI workflows, data bias handling.

• Learned how to align ML pipelines with real-world diagnostic requirements.