Agentic AI
Multi-agent orchestration with MCP tool boundaries and CRAG retrieval. The agent reads the request; typed contracts and exact solvers do the rest.
PhD in applied mathematics · shipping since 2018
AI Research Scientist & AI/ML Engineer
Math Agents Production
I build agentic AI systems and put them in front of real users: multi-agent orchestration, RAG, and MCP, running on Azure behind typed contracts, a test suite, and a human-approval gate. The PhD in applied mathematics is where I learned to prove a system works before it ships.
Open to roles in Germany, on-site, hybrid, or remote. French C2, English C1, German B2+.
What I do
Where I focus
Production ML
Pipelines that survive the handoff: containers, CI/CD, monitoring, and a rollback path. Deployment is part of the build, not a step afterward.
Deep learning systems
Distributed training and model parallelism on HPC clusters. Learning rates chosen from the theory, not from a search that costs GPU hours.
Research and evaluation
Convergence analysis published in Springer Nature, and the evaluation frameworks that tell you whether a model actually improved.
Selected work
Featured projects
All AI engineering projectsA deployed multi-agent system, an alignment pipeline, a retrieval stack, and a forecasting model that operators still run. Every number below opens onto the case study behind it.
Multi-agent · deployed
Agentic ERP supply-chain copilot
LiveA planner asks a supply question in plain English. The system does the arithmetic exactly rather than guessing at it, and stops for a manager on anything above $10,000.
A LangGraph agent routes the question to 1 of 7 exact solvers (OR-Tools, CVXPY, SciPy) and a pgvector CRAG pipeline. A Redis-backed human gate holds high-cost decisions, and 6 FastMCP typed contracts stand between the model and anything that executes.
- LangGraph
- FastMCP
- Neo4j
- pgvector
- OR-Tools
- Azure AKS
- Bicep
Frontier model alignment · active consulting
Agentic AI and post-training strategies
Making frontier models better at hard science problems, and designing the scoring so the improvement can be measured rather than asserted.
RLVR where the answer is objective, RLHF where it is not, and rubric criteria in between for graded scoring. Plus agent trajectory analysis and the preference datasets that feed SFT and DPO.
- RLHF
- RLVR
- SFT
- DPO
- Chain-of-Thought
- Rubric evaluation
Retrieval research · ongoing
Four-stage hybrid RAG pipeline for scientific QA
QASPER benchmarkThe research behind that chatboard: how to find the one relevant passage among 47,810, and when to admit there isn't one rather than inventing an answer.
SPECTER2 and BM25 retrieval fused with RRF, ColBERT v2 reranking, a calibrated CRAG gate, and Llama-3.1-8B generation with inline citations. One fix to answer extraction took ALCE Recall from 0.057 to 0.84.
- SPECTER2
- BM25
- ColBERT v2
- CRAG
- HyDE
- vLLM
- RAGAS
Forecasting · deployed
Intelligent fuel consumption and warning system
LiveTelecom sites in Cameroon were losing diesel and nobody could see where. This predicts what each site should burn and flags the ones burning more. Operators still run it.
A Random Forest regressor behind a Flask web app, with a deviation threshold at the mean plus 2 standard deviations, a monitoring dashboard, and exports for audits.
- Python
- Flask
- Scikit-Learn
- Pygal
- Render.com
- Outlier AI
- DeepLearning.AI
- Coursera
- Munich Center for Machine Learning
Certified in advanced agent coding, advanced prompt engineering, generative AI with large language models, and MLOps for production.
About
A bit about me
I started in Cameroon, building a fuel-forecasting app that base-station technicians ran themselves. Then I spent 6 years proving when gradient descent converges, and why.
Both halves show up in what I ship now: agentic systems that route decisions to exact solvers, retrieval that cites its sources, and a number attached to every claim. Deployment is where I finish, not where I hand off.