Agentic Systems Engineer
5+ years in AI · 20+ projects
Artificial intelligenceAutomationCustom software
I take a business need and deliver the system that runs in production — framing, build, rollout, handover.
Grenoble, France
French · English (bilingual)
The stack
01 / Services
A focused engagement or an end-to-end build: I adapt the scope to the decision, product or production problem you need to solve.
Turn a business use case into a testable direction before committing to a larger build.
Deliverables
Outcome
A decision-ready prototype and a clear next step.
Design and build the interface, APIs, data flows and AI layer as one coherent full-stack product.
Deliverables
Outcome
A usable product ready to operate and iterate.
Stabilise an existing AI feature across evaluation, observability, failure modes and deployment.
Deliverables
Outcome
An AI system the team can understand, maintain and trust.
02 / Projects
MCP server letting any agent act on what it sees across browser and real desktop (navigate/click/type/scroll/drag); returns text diffs of what changed instead of raw screenshots. GUI grounding fuses VLM detection + the AT-SPI accessibility tree; LiteLLM multi-provider router with cost-aware auto model-selection ranked from public benchmarks (MMMU, ScreenSpot-Pro, Video-MME); isolated software-GL sandbox so GPU/Flutter/Electron apps render. Installs into the major agent clients; files GitHub issues automatically. MIT.
My from-scratch deep-learning framework — where I rebuild things from first principles to actually understand them. Its spine is one generic data interface: classification, detection and reinforcement learning all flow through a single Dataset abstraction, pushed so far that a Gym RL environment is itself wrapped as a Dataset — the same dataloader and training loop then drive supervised and RL runs alike. Built on hintconf, a hand-written type-driven config system (type-hint coercion with no metaclass, lazy computed fields, no Pydantic), with tensor-subclass modalities (image/text/bbox) and hand-reimplemented ResNet · VGG · ViT · DETR (Hungarian matching) plus the DQN family. Ships a small scalar autograd with graph visualization, written to relearn backprop. ~11k LOC — openly a learning project. Below: an Atari Breakout rollout — the Gym RL environment wrapped as a Dataset — plus the 84×84 grayscale observation the pipeline feeds the agent.
The project I'm most attached to. A custom compiler turns 32 declarative "paradigms" (~1,400 lines of engineering principles) + a manifest into conditionally-loaded skills, invocable subagents and per-tool system prompts (Claude Code, Codex, Cursor, Copilot). Encodes a real multi-agent workflow (independent visual-critic gate, skeptical tester, frustration-analyzer, librarian-as-sole-editor). Prompt engineering as compiled, versioned software.
Framework-agnostic compute/visualization engine: SIMD/CUDA/ROCm/MKL/Metal kernels, WGSL/GLSL/SPIR-V shaders, virtualized rendering, C-ABI FFI to Python/JS/WASM.
Flutter + Rust (flutter_rust_bridge) learning app with an LLM content pipeline — local-embedding semantic dedup (fastembed + usearch), batched/cached inference, macro CRUD codegen. Actively maintained.
Parses CV/cover-letter PDFs (docling), classifies candidates with an LLM, files them to Google Drive and notifies the team on Slack — scheduled (cron, keyring creds). Built to take the manual sorting out of a hiring inbox.
A small open-source PyTorch utility that taps any nn.Module with forward hooks to pull out intermediate activations and feature maps — point it at a layer, run an input, get that layer's response back to inspect or visualise. Below: a ResNet's shallow-layer feature maps (the dog still legible per filter) beside a deep layer's abstract activations.
An MCP server that captures X11 windows and runs vision analysis over them, exposing desktop screen-grounding to any agent — a focused companion to interact for seeing what's on screen.
My published open-source Linux alias framework (since 2022) — self-documenting per-tool modules (git/apt/npm/django/nvidia/tensorboard/disk-mem/stats), incl. an interactive gum-driven multi-branch auto-rebase with conflict-guard + auto force-push; keyring-backed secret handling.
Games, student builds and first projects — 13 more, kept in the archive rather than shown here.
03 / Contact
Write to me directly, or start from the card so the subject is already set.
Open to interesting projects
Alan Blanchet EI — registered sole trader, France · SIRET 109 507 046 00018 · APE 6201Z · VAT not applicable — art. 293 B CGI
For a project
Tell me what needs to work, where you are today and the decision you need to make next.
Discuss a project View CV04 / About
One engineer across the product and AI stack.
5+ years shipping to production
Grenoble, France · remote
French (native) · English (bilingual — 3 years schooled in the UK)
Co-author, SPIE paper (2025)
What I work on
05 / Experience
AI / ML at the core, with regular cross-functional support — networking & infra, full-stack, account administration.
"R&D News" model watch, briefed to the whole team — a short briefing every 2 weeks on notable new models, architectures & techniques. Close follow of SOTA (LMArena · ARC-AGI · SWE-bench…).
06 / Research & teaching
Publication
Co-author (2nd of 6) on a peer-reviewed SPIE paper — CNN / SVM classification on biomedical multispectral imaging. A low-cost device for label-free, species-level identification of uropathogens; shows 240 spectral channels can be cut to <10 with limited loss.
Leroux, D., Blanchet, A., Davenas, C., Lac, L., Le Bihan, Y., & Fulchiron, C. (2025). A frugal multispectral imaging solution to identify uropathogens via SVM and ANN classification. Translational Biophotonics: Diagnostics and Therapeutics IV, Proc. SPIE Vol. 13934, 1393430.
Mentoring & teaching
Supervised a Master's research internship on LLM-based agents (defended, Grenoble INP/UGA) — a B2B company-data extraction & validation agent; benchmarked LLMs × MCP search tools (Tavily / Exa / DuckDuckGo; SIRET/SIREN validation against official French registries). Coached 5 engineering-student teams at ESISAR (Grenoble INP) on industrial AI projects — incl. a real-time speech-transcription tool needing domain-vocabulary performance.
07 / Skills
The capabilities behind web products and applied AI — grouped by domain. · 163 technologies
08 / Working approach
I build the smallest solution that solves the real need, then make it reliable enough to operate, evolve and hand over.
In practice
Scope, risks and trade-offs made explicit before the build
Tests, observability and documentation carried through to production
Just for fun
For fun, I wired my Claude usage to my Slack profile picture — so the team can tell at a glance when I'm about to run out (and when I'll be sad about it). A GPT image model paints the mascot through ten moods, Pillow stamps the exact usage bar on top (an image model can't draw precise widths), and a systemd timer reads my session usage from ~/.claude and pushes the matching frame to Slack via users.setPhoto.
A personal user token, scoped so it can only change my own avatar.
09 / Education
ML Engineer (work-study)
OpenClassrooms · Neovision
2022–24
AI-oriented robotics (work-study)
IMERIR
2021–22
DUT Computer Science (3rd/19 · Code Game Jam 2020)
IUT Montpellier-Sète
2019–21
Baccalauréat S, mention Bien
2019
3 years schooled in the UK — bilingual FR/EN
2010–13
The online ML degree was deliberate — local engineering schools weren't AI-focused enough; the online route freed time to experiment widely and level up faster.
Video archive
