Hi, I'm

Ayoub Ben Chaliah

Senior AI Engineer

AI Engineer building high-performance inference systems and reasoning models. I write CUDA kernels, MLIR/LLVM compiler passes, and build reward models. Creator of AdaLLM and Datarus-R1.

0+ GitHub Stars
0 arXiv Papers
0+ Years Experience
AI

Ask me anything

RAG-powered AskMeAnything
Hey! I'm Ayoub's AI assistant. I can tell you about his work building high-performance inference systems, CUDA kernels, and reasoning models like Datarus-R1. Ask me about:
  • His projects — AdaLLM, Datarus-R1, TensaLang, and more
  • Technical skills — CUDA, MLIR/LLVM, vLLM, distributed training
  • Professional experience and research publications
  • His approach to GPU optimization and model architecture
What would you like to know?

About Me

I'm an AI Engineer based in Paris with deep expertise across the full stack of modern AI systems. My work spans from writing fused CUDA and Triton kernels that squeeze every FLOP out of GPU hardware, to designing MLIR compiler passes that generate optimized code, to training reasoning models that rival systems with twice the parameters.

I co-created Datarus-R1-14B, a reasoning model that outperforms 32B+ systems on AIME and LiveCodeBench while consuming 18–49% fewer tokens. I also built AdaLLM, an NVFP4-first inference engine that achieves ~240% VRAM reduction on Ada Lovelace GPUs.

I led development of CyberDefenderAI, the pilot AI security solution for EnBW — one of Europe's largest energy companies and a critical infrastructure operator in Germany. The system is deployed at their Cyber Defense Center, autonomously hunting threats through multi-step reasoning and sandboxed tool execution.

Previously, I led compiler engineering at ChainsAtlas, where I extended LLVM backends and built a Turing-complete on-chain virtual machine in Solidity. I hold a Master's in AI from IA School Paris and a Bachelor's in Statistics & Data Science from ENSAI.

Location

Paris, France

Experience

5+ years in AI/ML

Education

Masters in Artificial Intelligence (BAC+5)

Languages

French · English (Fluent)

Experience

Senior AI Engineer

ClaireChains SAS · Paris, France

Jan 2023 — Present

Led end-to-end design and deployment of AI infrastructure spanning reasoning model research, custom GPU kernel development, distributed training, and high-performance inference optimization.

Reasoning Models & Alignment

  • Led development of CyberDefenderAI, the pilot AI security tool for EnBW's Cyber Defense Center — a security-focused reasoning model trained via SFT + GRPO with multi-step tool calls and dense per-action rewards
  • Co-created Datarus-R1-14B, trained on 144K trajectory episodes using dual-reward GRPO and Hierarchical Reward Modeling, outperforming 32B+ models on AIME and LiveCodeBench

GPU Kernels & Inference

  • Built AdaLLM, an NVFP4-first inference runtime for RTX 4000 series with FP8 KV-cache and custom decode kernels — ~240% VRAM reduction
  • Implemented custom CUDA and Triton kernels for Ada/Hopper architectures: FlashAttention variants, fused MoE routing kernels, PTQ/QAT pipelines
  • SSD-based KV-cache offloading using NVIDIA GDS with speculative prefetching for long-context generation

Compiler Infrastructure (C++)

  • Designed custom MLIR passes and LLVM lowering paths for optimized inference codegen across CUDA and Triton
  • Worked across dialects (Linalg, Vector, GPU, SCF, Affine) for tiling, vectorization, and lowering to AVX2/AVX-512

Lead Compiler Engineer

ChainsAtlas

Dec 2022 — Dec 2025

Led all engineering for a cross-chain virtualization platform enabling execution of Web2 code (C, Python, JavaScript) on EVM and non-EVM blockchains.

  • Extended LLVM backend with custom passes for instruction selection, register allocation, and code generation targeting a custom on-chain ISA
  • Built a Turing-complete 16-bit VM interpreter in Solidity with fetch/decode/execute loop and register file
  • Exposed EVM primitives to C via compiler intrinsics that lower directly to native opcodes
  • Shipped cross-chain interoperability execution layer across EVM and Solana

Machine Learning Engineer

Idatase GmbH · Berlin, Germany

Apr 2021 — Jan 2022

Developed and deployed time series forecasting models on distributed systems for IoT and energy prediction.

  • Deployed LSTM, Temporal Fusion Transformer, and ARIMAX models for energy consumption prediction
  • Collaborated with Tilia GmbH on power consumption analytics: DTW, K-means clustering, hierarchical consumer segmentation
  • Built anomaly detection pipelines (GMMs, autoencoders) and high-performance graph-based REST APIs for digital twins

Featured Projects

CyberDefenderAI

Pilot AI security tool for EnBW's Cyber Defense Center. Security-focused reasoning model with SFT + GRPO, multi-step tool calls, and dense per-action reward training on simulated attack episodes.

GRPOSFTCybersecurityRL
Learn More →
80

Superposition Transformer

Novel MoE architecture using B-spline blending and autoencoders to merge base and fine-tuned model representations, mitigating catastrophic forgetting with minimal parameter overhead.

MoEB-SplinesAutoencodersPyTorch
224

Datarus JupyterAgent

Multi-step reasoning pipeline built on Datarus-R1-14B. Autonomous data analysis agent that reasons, writes code, executes, and self-corrects inside Docker-isolated Jupyter notebooks.

AgentsReActDockerJupyterPython
View on GitHub Learn More →
70

TimeSeriesGAN

GANs for time series analysis: synthetic data generation, anomaly detection, and interpolation. Uses Optuna for hyperparameter optimization and MLFlow for experiment tracking.

GANsTime SeriesMLFlowOptuna
View on GitHub Learn More →

Technical Skills

GPU & Kernels

CUDATritonROCm/HIPFlashAttention Fused MoE KernelsKV-Cache Optimization FP8/FP4/INT4 QuantizationGPTQAWQ GGUFNVFP42:4 Sparsity

Inference & Serving

vLLMTensorRT-LLMTGIllama.cpp Continuous BatchingSpeculative Decoding KV-Cache OffloadingNVIDIA GDSPrefix Caching

Compilers

MLIRLLVMLinalg DialectVector Dialect GPU DialectTiling/Fusion Passes AVX2/AVX-512Code Generation

Training & Alignment

GRPOPPODPORLHFSFT Reward Modeling (ORM/PRM/HRM)Synthetic Data Curriculum Learning

Distributed Systems

DeepSpeedRayInfiniBand/RoCE Multi-Node TrainingTensor Parallelism Pipeline ParallelismFSDP

Frameworks & Hardware

PyTorchTransformersDeepSpeed TRLOpenRLHFAxolotl A100H100/H200B200MI300X PythonC++CCUDA C

Get In Touch

I'm open to new opportunities where I can push the boundaries of AI systems — whether that's building faster inference engines, training smarter models, or designing compiler infrastructure for the next generation of hardware. Let's talk.

AI

Ask me anything

RAG-powered AskMeAnything
Got questions? Ask away!