Applied AI · Remote

Applied AI developer for agents, RAG and business automation.

I build AI systems connected to real business processes: internal copilots, AI agents, document automation, semantic search over private documentation and integrations with Python/FastAPI backends.

AI AgentsRAGPythonFastAPIAutomation

Applied AI

AI with operational value.

Useful AI is not just a chatbot. It needs data, rules, integrations, logs, validation and a clear business process.

AI 01

AI agents

Agents connected to business rules, APIs and internal workflows.

AI 02

RAG systems

Semantic search over private documentation, manuals, PDFs and internal knowledge.

AI 03

Document automation

Extraction, classification and summaries from emails, tickets, invoices and operational documents.

AI 04

AI for eCommerce

Product content, support assistants, recommendations, cart recovery and post-sale workflows.

AI 05

Computer vision

Image analysis, content classification and visual data workflows.

AI 06

Backend integration

AI APIs integrated into Python/FastAPI systems with logs, limits and validation.

Applied AI

AI that connects with real business processes.

The value is not in adding a chatbot. The value is in designing a controlled workflow: data, retrieval, permissions, logs, validation and integration with existing tools.

01

Internal copilots

Assistants for teams that need to search private documentation, answer recurring questions, draft replies or prepare operational decisions with human review.

02

RAG over private knowledge

Semantic search and controlled answers over PDFs, manuals, catalogues, procedures, policies and technical documentation.

03

AI automation

Classification of emails, document extraction, summaries, generated drafts, eCommerce workflows and API-connected automation with Python/FastAPI.

Method

From AI idea to maintainable software.

I start by mapping the process, defining risk and building a small measurable prototype before moving to production.

01

Process map

Inputs, outputs, exceptions, volume, current tools and cost of error.

02

Technical design

Model, prompts, retrieval, APIs, logging, permissions and cost control.

03

Measurable prototype

A small first version to validate accuracy, speed, cost and usefulness.

04

Controlled production

Integration into the real workflow with monitoring and human review where needed.