Malcom Mudhungwaza
I build LLM systems that hold up in production, and research where they fail.
Agentic AI, RAG, evals and LLM serving — designed end to end and measured against what the system is actually for. Alongside it, doctoral research on guardrails: where safety alignment breaks down across language and modality, and whether the benchmarks measuring it test refusal or reading ability.
- Senior AI EngineerGenAI, LLM & agentic systems
- Ph.D. ResearcherAI safety & alignment
- 5+ yearsproduction LLM & ML systems
Malcom Mudhungwaza
Senior AI Engineer · Abu Dhabi, UAE
Core capability
AI agents, RAG, software engineering and platforms
- AI Agents & MCPTool-using agents over Model Context Protocol, orchestration that survives a restart, and failure rates measured per topology.
- Voice AgentsStreaming ASR into dialogue into speech synthesis, budgeted per hop against time to first audio rather than total generation.
- RAG & Vector SearchHybrid dense and lexical retrieval with re-ranking, and the filtered-ANN failure that returns nothing while reporting success.
- Multimodal AIVision-language extraction over scanned pages, charts and photographs, where the input was never clean text to begin with.
- Software EngineeringThe product around the model: backend services, relational and vector data layers, queues, and deployment that holds under load.
- Platforms & InfrastructureContainerised services with CI/CD, tracing, caching with a measured hit rate, and per-tenant budgets that stop a runaway.
- Evals & GuardrailsLLM-as-judge harnesses calibrated against human labels, CI regression gates, and doctoral research on what safety benchmarks actually measure.
- Post-TrainingSupervised fine-tuning and preference optimisation, with the objective chosen against the feedback actually available.
- LLM Serving & InferenceSelf-hosted open-weights models with quantisation, sized against a latency target and a cost per million tokens.
- Model InternalsAttention and KV cache arithmetic, MoE routing, long-context behaviour — the depth that makes an optimisation predictable.
Scope
Five domains, end to end
AI agents and voice, RAG and multimodal, the software platform underneath, and the model internals when a system has to get cheaper or faster. Each domain is backed by published code.
AI Agents & Voice Agents
5 reposSystems that use tools, call other systems and hand off to people. The engineering is in the failure modes, not the happy path.
- LangGraph
- LangChain
- MCP
- Durable execution
- Streaming ASR
RAG & Multimodal AI
4 reposGetting the right evidence in front of the model, including when the input is a scanned page or a photograph rather than clean text.
- pgvector
- FAISS
- Pinecone
- HNSW tuning
- Hybrid search
Software Engineering & Platforms
3 reposThe product around the model. Most AI features fail on ordinary engineering — schema, concurrency, caching, deployment — long before they fail on model quality.
- Python
- FastAPI
- C++
- REST
- WebSockets
LLM Engineering & Evals
7 reposAdapting open models to a domain, and the measurement that decides whether a change shipped an improvement or a regression.
- LoRA
- QLoRA
- DPO
- GRPO
- TRL
AI Internals & Optimisation
7 reposWhat a token costs and why. Useful when a system has to get cheaper or faster and the obvious levers have already been pulled.
- vLLM
- llama.cpp
- Continuous batching
- KV cache
- AWQ
What I build
Systems, not demos
The things I am usually brought in to design and ship. Each has a version running against real traffic, and a version published here as open research.
Agentic document pipelines
Multimodal extraction into structured output, LLM reasoning over the result, confidence gating per document class, and a human review path for the cases that should not be automated.
RAG systems
Hybrid dense and lexical search with re-ranking, chunking chosen against the document shape, and retrieval quality measured separately from generation quality.
LLM serving & inference optimisation
Quantised models behind an inference gateway, sized against a stated latency target and a cost per million tokens, with routing and per-tenant budgets.
Post-training & domain adaptation
Supervised fine-tuning and preference optimisation on open-weights models, with the objective chosen against the feedback actually available rather than the newest paper.
Evals & CI regression gates
Golden datasets, LLM-as-judge scoring calibrated against human labels, and regression gates that fail a build when quality drops by a detectable margin.
Voice agents & multimodal
Streaming ASR into dialogue orchestration into speech synthesis, budgeted per hop against time-to-first-audio rather than total generation time.
Agentic AI & MCP servers
MCP servers exposing internal systems as tools, orchestration with checkpointing that survives a restart, and topology chosen from the failure mode that matters most.
Platform layers & observability
Async services with bounded concurrency, retry classification at the transport boundary, caching with a measured hit rate, and schemas read against their query plans.
Research
A doctorate on where safety alignment breaks
Ph.D., Artificial Intelligence & Machine Learning, in progress. The dissertation asks a question that current benchmarks cannot answer:
How much of the apparent cross-modal safety gap is a reading-ability artifact rather than an alignment gap?
A model that cannot read a request scores the same as one that read it and refused. Separating the two is the contribution.
- Field
- AI safety and alignment
- Working papers
- Multi-Agent Orchestration with Model Context Protocol: A Framework for Reliable Tool-Augmented LLM SystemsPreprint in preparation · arXiv, 2026Safety Alignment Across Language and Modality: Perception Confounds in Multimodal LLM Guardrail TransferPreprint in preparation · arXiv, 2026
- Open research
- 26 repositories · 950 tests
Built with
- PyTorch
- Transformers
- TRL
- vLLM
- AutoAWQ
- LangGraph
- FastAPI
- PostgreSQL
- pgvector
- Redis
- FAISS
- sentence-transformers
- rank_bm25
- ONNX Runtime
- faster-whisper
- piper
- OpenCV
- Ultralytics
- NumPy
- SciPy
- Matplotlib
- Pydantic
- httpx
- anyio
- arq
- OpenTelemetry
- pytest
- datasketch
- fastText
- C++
- Python
- WebSockets
Engineering
Perception, robotics and on-device inference
Earlier work, written up in full. Real-time detection on embedded hardware, sensor fusion and SLAM navigation, and medical imaging — the systems background the LLM work is built on.
Computer Vision & AI
Cancer Detection Model
A convolutional network for early skin-cancer detection on the HAM10000 dataset, built around an EfficientNet-B4 backbone with spatial and channel attention, Grad-CAM explanations, and five-fold stratified cross-validation.
TensorFlow, CNN, Transfer Learning
Read the write-up
Robotics & Computer Vision
Autonomous Drone Vision
A real-time aerial detection stack running YOLOv9 on NVIDIA Jetson through TensorRT, with DeepSORT tracking, CUDA preprocessing and ROS2 integration on a custom drone platform.
YOLOv9, NVIDIA Jetson, TensorRT
Read the write-up
Robotics Engineering & AI
Autonomous Fire Fighter Robot
An autonomous ground robot combining YOLOv8 flame detection with LiDAR SLAM and A* path planning, navigating to and suppressing fires in cluttered indoor environments.
YOLOv8, ROS2, SLAM, Embedded Systems
Read the write-up
AI Assistant & NLP
Mini AI Assistant
A local-first assistant built on DistilBERT intent classification and BiLSTM-CRF entity extraction, exported to ONNX for on-device inference on desktop and Raspberry Pi.
Python, BERT, TensorFlow
Read the write-up
Contact
Get in touch
Happy to talk about anything here, or about LLM systems, evaluation and serving generally. Mentioning a repository by name gets you a faster and more useful answer.
- Based in
- Abu Dhabi, UAE
- GitHub
- github.com/malcomzww
- linkedin.com/in/malcomzw