Skip to content

AI Software Engineer · WineConX · Berlin, Germany

Allen Xavier

I architect the AI systems behind a production platform. Agent design, the domain models they operate on, and the infrastructure that runs them.

See the architecture

Résumé on request

My résumé is not available to download. Message me on LinkedIn and I will send it over.

Message me on LinkedIn
EmailGitHub
ARCHITECTURE
Agent systems, domain design
INFRASTRUCTURE
Terraform, cloud
RESEARCH
IEEE ITSC 2025
01

The architecture

How the platform is put together, and why it is put together that way.

Four systems on one platform, built on the same spine. What changes between them is the domain and the agents. What does not change is where the boundaries sit.

  1. Entry

    What starts a run

    • Campaign brief
    • Traveller chat
    • Brand site
  2. Agents

    Specialists that each own one craft

    • Director
    • Script writer
    • Photographer
    • Cinematographer
    • Profile
    • Planner
    • Booking

    LangGraph · LangChain · MCP · Function calling

  3. Domain

    Business logic, independent of any provider

    • Campaign
    • Itinerary
    • Brand surface

    Python · FastAPI · Node.js

  4. Adapters

    Swappable, held at the edge

    • LLM providers
    • Media generation
    • Booking APIs
    • Structured data

    OpenAI · Anthropic · Gemini · Chroma · pgvector

  5. Infrastructure

    Terraform, provisioned against demand

    • Environments
    • Instance lifecycle
    • Deploy

    Terraform · AWS · GCP · Docker · GitHub Actions

The layering is deliberate. Agents sit above the domain and never below it, so an agent can be rewritten without the business logic noticing. Providers sit at the edge behind adapters, so changing a model is a configuration change, not a migration. Infrastructure is described in the same repository as the thing it runs.

That is what let four products share one platform instead of becoming four codebases. The media house and the destination desk have almost nothing in common at the domain level, and almost everything in common below it.

PRINCIPLES BEHIND IT

Design for the failure modes

The interesting problems are rarely the model call. They are retries, partial results, cost, and knowing when an agent should stop rather than keep trying.

Boundaries are the deliverable

Deciding what belongs inside the domain and what stays at the edge is the actual work, and holding that line when a deadline argues otherwise is most of it.

Prototype and production share a codebase

A demo that has to be rewritten to ship was never evidence it would ship. The path to production is a design constraint, not a later phase.

Write for machine readers too

Increasingly the first reader of anything you publish is a model. How a system describes itself now shapes how it is found and repeated.

02

Systems

What that architecture is carrying.

Automated media

In production

An agent-orchestrated media house

A director, a script writer, a photographer and a cinematographer, running as agents. Together they produce publishable marketing media end to end.

Campaign briefDirector agentScript writerPhotographerCinematographerAssemble & reviewPublish
StepAgent

Modelling agents on production roles is what makes it work. A director owns coherence and delegates to specialists that each own one craft. That holds up far better than one general-purpose agent, and every role can be improved on its own.

Generation providers stay at the edge of the system. Models change constantly, so the domain logic should not change with them.

AI AgentsAgentic WorkflowsLLM SystemsAutomated MediaDomain-Driven Design
Production
Running for wine brands
Text · Image · Video
Generated modalities

Destination management

In production

An automated destination management desk

The work a destination management agent does by hand. Profiling a traveller, planning the trip, sourcing and booking each activity, running as a chain of agents.

A profile agent reads the conversation for what the traveller actually wants. A planner agent turns that into a day by day itinerary. A booking agent routes each activity to the relevant provider, asks whether it can be had, and books it.

Every activity carries its own state. It starts pending, and only a successful booking moves it to confirmed. Otherwise it is cancelled, so the itinerary describes what is actually held rather than what was proposed.

AI AgentsConversational AIStructured OutputState MachinesThird-party APIs

Infrastructure as code

Demand-driven instance automation

Terraform provisions and de-provisions instances for digital brand solutions, scaling with the demand of each brand workflow.

Instances come up and go down as workload requires, with lifecycle handling robust enough to run unattended. Provisioning expressed as code lets capacity track demand without becoming fragile.

TerraformInfrastructure as CodeCloud ArchitectureAutomation

Discoverability

Current focus

AI SEO for brands

Making a brand legible to the systems that now answer questions about it. Structuring a site so an answer engine retrieves and cites it correctly, not just so a crawler ranks it.

A crawler and an answer engine read the same site for different reasons. One builds an index to rank. The other retrieves passages to summarise and attribute. Optimising for the first is twenty years old. Most brands are invisible to the second.

The work is to give a site a machine-readable surface. Schema.org data describing what the brand actually is, semantic markup that survives extraction, explicit machine-readable context. The real question becomes what a model says about the brand when nobody is checking, which is closer to brand safety than marketing.

AI SEOAnswer Engine OptimisationStructured DataSemantic MarkupSchema.org
Retrieval
Optimised for citation, not only ranking
Schema · llms.txt
Machine-readable surface
03

Experience

Mar 2026 to PresentCURRENT

AI Software Engineer

WineConX · Berlin, Germany

Building the AI systems behind WineConX’s digital marketing platform for the wine industry: an agent-orchestrated media production pipeline, a conversational itinerary system, the Terraform-managed infrastructure they run on, and AI SEO for client brands.

  • Own the AI systems end to end: agent design, the architecture around them, and the infrastructure they run on.
  • Applied domain-driven design so model providers can be swapped without reworking the core.
  • Took systems from prototype to production, on Terraform environments that run unattended.
AI AgentsAgentic WorkflowsLLM SystemsSoftware ArchitectureDomain-Driven DesignTerraformAI SEONode.js

Mar 2024 to Feb 2026

Research Assistant

FZI Research Centre · Karlsruhe, Germany

Applied research on multimodal LLM systems and graph neural networks, spanning automated UX evaluation and epidemiological risk prediction.

Nov 2024 to May 2025

Master's Thesis: EffiComm

FZI Research Centre · Karlsruhe, Germany

Bandwidth-efficient multi-agent communication for cooperative autonomous driving, published at IEEE ITSC 2025.

Feb 2023 to Mar 2024

Software Developer (Werkstudent)

Vanory · Karlsruhe, Germany

RTOS firmware and edge AI for consumer IoT lighting hardware shipping at production volume.

50x
Power reduction, 1A to 20mA
500+
Devices in production

Jan 2023 to Jan 2024

Software Developer (HiWi)

RITA Project · Karlsruhe, Germany

Computer vision and photogrammetry for terrain understanding in medium-scale robotic systems.

EARLIER

  • Mar 2022 to Sep 2022Associate Software DeveloperGupshup · Mumbai, India
  • Jan 2022 to Feb 2022Machine Learning InternLife Spark Technology, IIT Bombay · Mumbai, India
  • Aug 2021 to Dec 2021Embedded Systems DeveloperMetwiz Materials · Maharashtra, India
04

Selected work

A few projects that show the range, from cooperative perception to microcontroller-scale inference.

CAPABILITIES

AI engineering
AI AgentsMulti-Agent SystemsAgentic WorkflowsLLM OrchestrationRetrieval-Augmented Generation (RAG)Function CallingTool UseModel Context Protocol (MCP)Structured OutputPrompt EngineeringLoRA / QLoRA Fine-tuningHybrid RetrievalRerankingEmbeddingsMulti-Modal LLMsEvaluation & Observability
Models & providers
OpenAI APIAnthropic ClaudeGoogle GeminiVertex AIHugging FaceOllamavLLM
Frameworks & retrieval
LangChainLangGraphVector DatabasesChromapgvectorBM25n8n
Architecture & design
Software ArchitectureDomain-Driven DesignSystem DesignAPI DesignEvent-Driven DesignArchitectural Patterns
Backend & data
FastAPINode.jsREST APIsPostgreSQLMongoDBMySQL
Cloud & infrastructure
TerraformInfrastructure as CodeAWSGoogle CloudDockerKubernetesGitHub ActionsJenkinsLinuxGit
Languages
PythonTypeScriptJavaScriptC++CBash
Machine learning
PyTorchTensorFlowGraph Neural NetworksComputer VisionOpenCVscikit-learnData Analysis
Discoverability
AI SEOSEOStructured DataSemantic MarkupSchema.org
Foundations
Embedded C/C++FreeRTOSEdge AITinyMLIoTMQTTReal-Time Systems
05

Research foundation

Two years of applied research underneath the engineering. Multi-agent perception, graph neural networks, and edge inference.

  1. EffiComm: Bandwidth Efficient Multi-Agent Communication

    IEEE International Conference on Intelligent Transportation Systems (ITSC) · 2025

    Graph neural networks with a mixture-of-experts architecture cut vehicle-to-vehicle perception bandwidth by 83.7% while holding 92% detection accuracy.

    83.7%
    Bandwidth reduction, 11.64MB to 1.90MB
    92%
    Detection accuracy retained
    ITSC 2025
    IEEE conference proceedings
  2. Patient Monitoring & Assisting System

    IEEE International Conference on Computational Science and Technology · 2022

    A wearable monitoring system combining sensor instrumentation with on-device inference for continuous patient assessment.

  3. Unknown Terrain Modelling using 3D Mapping

    International Conference on Computing Methodologies and Communication · 2021

    Photogrammetric 3D reconstruction for navigating previously unmapped terrain in robotic systems.

06

Get in touch

Open to conversations about AI engineering and architecture roles.

EmailGitHubLinkedIn

Résumé on request

My résumé is not available to download. Message me on LinkedIn and I will send it over.

Message me on LinkedIn