You will get a custom AI agent, MCP server or RAG system built in Python or Go
Project details
Most AI agent demos fall over in production. I build the kind that does not, because the hard part is rarely the prompt - it is the engineering around it.
I am a senior backend developer with 15+ years of experience, including 11 years on a cloud billing platform acquired by Google. Over the past year I have been building with agents specifically, and hold current certifications from Anthropic (MCP, Claude Code) and IBM (RAG and Agentic AI, LangGraph/CrewAI/AutoGen).
What I build:
• MCP servers exposing your tools, APIs and data to Claude or other LLM clients
• AI agents and multi-agent workflows with LangGraph, CrewAI or plain Python
• RAG pipelines: chunking, embeddings and retrieval that returns the right context
• LLM integrations into existing backends, in Python or Go
• Evaluation, so you can tell whether it works instead of guessing
Plenty of people can wire up a demo. Fewer build it as a real service with error handling, tests, logging and a sane cost profile. That part is backend engineering, which I have done for 15 years.
Tell me what you want the agent to do and I will tell you honestly whether an agent is even the right tool.
I am a senior backend developer with 15+ years of experience, including 11 years on a cloud billing platform acquired by Google. Over the past year I have been building with agents specifically, and hold current certifications from Anthropic (MCP, Claude Code) and IBM (RAG and Agentic AI, LangGraph/CrewAI/AutoGen).
What I build:
• MCP servers exposing your tools, APIs and data to Claude or other LLM clients
• AI agents and multi-agent workflows with LangGraph, CrewAI or plain Python
• RAG pipelines: chunking, embeddings and retrieval that returns the right context
• LLM integrations into existing backends, in Python or Go
• Evaluation, so you can tell whether it works instead of guessing
Plenty of people can wire up a demo. Fewer build it as a real service with error handling, tests, logging and a sane cost profile. That part is backend engineering, which I have done for 15 years.
Tell me what you want the agent to do and I will tell you honestly whether an agent is even the right tool.
AI Algorithms
Large Language ModelAI Applications
AI Chatbot, AI-Generated Code, Conversational AIAI Development Language
PythonAI Models
ChatGPT, GPT-4, LLaMAWhat's included
| Service Tiers |
Starter
$300
|
Standard
$800
|
Advanced
$2,000
|
|---|---|---|---|
| Delivery Time | 5 days | 10 days | 21 days |
Number of Revisions | 1 | 2 | 3 |
AI Model Integration | |||
Batch Normalization | - | - | - |
Database Integration | - | ||
Detailed Code Comments | |||
Image Upscaling | - | - | - |
MLOps | - | - | - |
Model Deployment | - | - | - |
Model Documentation | - | - | - |
Model Monitoring | - | - | - |
Model Testing & Optimization | - | - | - |
Model Tuning | - | - | - |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | - | - | - |
Setup File | - | - | - |
Source Code |
Frequently asked questions
1 review
(1)
(0)
(0)
(0)
(0)
This project doesn't have any reviews.
AH
Adrian H.
Aug 23, 2026
Laravel + React Developer — Bug Fixes & Small Features on Production Booking Platform
Andy was easy to work with. He understood fast what I needed to be implemented.
I provided all the resources that he needed and the implementation was exactly what I have required and on time.
Easy to talk to, he was available for explanation and clarification, I will surely work with him again in the future.
I provided all the resources that he needed and the implementation was exactly what I have required and on time.
Easy to talk to, he was available for explanation and clarification, I will surely work with him again in the future.
About Andrei
Senior Backend Engineer | Go, Python, PHP | APIs & AI Integration
Iasi, Romania - 5:22 pm local time
I've been developing production software for 15+ years, including 11 years working on a multi-cloud marketplace and billing platform acquired by Google. The platform processes millions of dollars in monthly billing for tens of thousands of businesses and close to 100,000 users, backed by a 7 TB MySQL database and BigQuery reporting pipelines.
I own backend services there end to end: Go microservices using gRPC and REST, usage rating and invoicing pipelines for AWS, Azure and Google Cloud, database schema design, query optimization on high-volume billing tables, and the Angular/TypeScript applications on top.
What I can help you with:
Backend services, REST APIs and microservices in Go, Python/FastAPI or PHP
Debugging existing systems — from straightforward bugs to race conditions, performance issues and production data problems
MySQL schema design, indexing, query optimization and safe migrations
Third-party APIs, payments, billing and external service integrations
AI/LLM integrations, agents, tool calling, MCP and RAG systems
BigQuery pipelines, reporting and large-scale data processing
Full-stack work when needed using Angular and TypeScript
Dockerized applications and production deployments
I'm also a co-founder of FranceRent, a live tours and experiences marketplace in France handling around 100 bookings per month. I built its entire backend and full administration platform, including the admin frontend, and continue to maintain and operate it. This gives me experience not only building software, but also running a real online business where reliability, payments and operational workflows matter.
How I work: I clarify the problem before writing code, give realistic estimates, and deliver maintainable, tested work with clear documentation. I am comfortable taking ownership of an existing codebase as well as building new systems from scratch.
Send me a short description of what you're trying to build or fix. I'll tell you whether it's a good match for my experience and how I would approach it.
Steps for completing your project
After purchasing the project, send requirements so Andrei can start the project.
Delivery time starts when Andrei receives requirements from you.
Andrei works on your project following the steps below.
Revisions may occur after the delivery date.
Define the task and the tools
We agree what the agent must do, which tools and data it needs, and how we judge success.
Build and evaluate
I implement the agent or pipeline, wire up the tools and data sources, and evaluate it against real examples rather than a single happy path. You see progress as it goes, not just at the end.