Chamel Nadir BouachaEngineering
I build the systems my research needs and apply the same engineering discipline at work.
Junior Full-Stack Developer, Momentum Worldwide · July 2026 – present
Featured
Python/FastMCP server
AI-oriented function spanning MCP server engineering, AI enablement, Salesforce engineering, and enterprise technical assessment.
Built and deployed a Python/FastMCP server converting existing repository business logic and skills into MCP tools, resources, and prompts for internal operations users.
No public artifact (employer work).
IRCHAD — Indoor Navigation for the Visually Impaired
Indoor navigation system for visually impaired users, built as a fourth-year ESI team project across twelve repositories covering web, mobile, and backend services.
Team Lead and AI Developer for the team; built the architectural-floor-plan preprocessing pipeline and designed the evaluation protocol.
89% mAP for doors, walls, and windows
Automatic Code Optimization
Built a pipeline that converts PyTorch models into MLIR intermediate representations using the Linalg and TOSA dialects.
Fig. 1 The conversion path in Model_To_MLIR: a PyTorch model is imported through torch-mlir’s FX importer and emitted as an MLIR module in the Torch dialect, Linalg-on-tensors or TOSA, depending on the selected output type. Drawn from the public repository’s examples. The dialect conversions themselves are torch-mlir’s. No performance figures.
Research systems
Temporal annotation pipeline
A temporal annotation pipeline extended from temporal-expression detection and normalization to event extraction, event-to-time linking, and document-creation-time anchoring. The annotator combines rules, spaCy, and a small language model. Its annotation output contributed data used for the work that became WaTE.
Temporal RAG for Healthcare
A retrieval-first architecture that combines semantic relevance with explicit temporal constraints over longitudinal healthcare information, addressing temporal granularity, event-time anchoring, provenance, and retrieval-time consistency.
Other selected work
Transformer from scratch
Implemented the Transformer architecture in PyTorch, covering embeddings, multi-head attention, positional encoding, and encoder-decoder blocks, following "Attention Is All You Need".
Multi-agent analytics pipeline
Architected and deployed a modular multi-agent analytics pipeline on GCP Cloud Run that processed scheduled Google Analytics data into behavioural reports and UI/UX recommendations, with CI/CD through Cloud Build.
FLY Page — AI Landing Page Generator
Stateful multi-agent landing-page generator built with LangGraph and LangChain, orchestrating four specialized LLM agents with conditional routing and a web-scraping fallback.
HTPL Compiler
Compilation pipeline in C with Flex and Bison: lexical analysis, parsing, semantic analysis with type checking, and quadruple generation.
Samsung Innovation Campus capstone
End-to-end analytics pipeline for Algerian Baccalaureate educational video content: YouTube Data API v3 collection, a data-driven Bac-content filter using channel priors and TF-IDF term discovery, engineered engagement features, predictive modelling, and a RAG-based recommendation agent over a local knowledge base.