Work

Projects

A selection of research projects, production deployments, and engineering work.

Production RAG & LLM System — Mental Health NLP

Led a team of 30+ engineers at Omdena to build and deploy a production LLM + RAG pipeline in 9 weeks from prototype to live AWS deployment. The system processed unstructured, culturally varied mental health and wellbeing data with significant noise: inconsistent language, missing fields, cross-cultural variation.

Diagnosed production data quality failures and led implementation of a user feedback loop (RLHF) to close the test/production performance gap. Designed evaluation loops, structured output schemas, and validation logic to reliably extract signal from subjective text. Owned the full pipeline: ingestion, embeddings, model integration, API deployment, and stakeholder delivery.

LangChain RAG Embeddings RLHF AWS REST API Python

Omdena · Feb – Apr 2024 · Remote

Intelligent Financial Planning System

Built an LLM + RAG-based financial planning system using LangChain agent workflows, deployed on AWS with full API integration. Implemented structured output validation and fallback logic to ensure production-grade reliability of AI responses.

LangChain LLM agents AWS Structured outputs Python

OptimumAI Labs · Apr – Jun 2024 · Remote

Deep RL for 5G / Wi-Fi Traffic Steering ongoing

Developing reinforcement learning algorithms (PPO, DQN, LSTM) for real-time multi-access traffic steering in 5G/Wi-Fi heterogeneous networks, framed as sequential decision-making under uncertainty. Building robust data pipelines for real-time telemetry processing and policy evaluation on Linux servers.

Co-authoring: Multi-Access Traffic Steering in Real-World 5G with Deep Reinforcement Learning (paper in preparation).

PPO DQN LSTM Python Linux Telemetry

Leibniz Universität Hannover · Apr 2025 – Present

GPS Sensor Fusion Pipeline

Multi-sensor data fusion pipeline for real-time GPS localisation using Kalman filtering. Fused inconsistent signals from multiple GPS sources into a single reliable state estimate, handling measurement noise and sensor dropouts.

Kalman filter Sensor fusion Python MATLAB

Universität Duisburg-Essen · Jun – Jul 2020

Autonomous 3-DOF Greenhouse Robot

Developed an autonomous robot system for greenhouse plant care with real-time sensor integration, motion planning, and control. The robot performed autonomous navigation and plant maintenance tasks without human intervention.

Arduino MATLAB Simscape SolidWorks Python Control systems

Universität Duisburg-Essen · Nov 2020 – Feb 2021

Neural Network System Identification & NMPC

MSc thesis: benchmarked NARX, LSTM, Bi-LSTM, and GRU architectures for nonlinear system identification, recovering reliable behavioural models from noisy, incomplete observations. Implemented a data-driven Nonlinear Model Predictive Controller (NMPC) and validated it in MATLAB.

NARX LSTM Bi-LSTM GRU NMPC MATLAB Python

Universität Duisburg-Essen · 2022 · MSc Thesis