LeonardoConti

Founding engineer building applied AI and LLM systems for the creator economy: agents, automation, and the backends they run on.

• Designed production infrastructure for AI agents, orchestration, tool use, retrieval, long-term memory, and reliable execution.
• Built systems that automate creator conversations, improve monetization workflows, and support platform-scale AI operations.
• Implemented classification, moderation, and guardrail systems for safer and more consistent AI behavior.

Led production LLM feature work across Replika's large-scale consumer AI companion experience for more than 38 million users.

• Owned technical direction and delivery for LLM-powered product work across chat, companion behavior, and backend reliability.
• Improved conversation quality and reliability for the next generation of AI companion systems.

Built production-grade multi-agent LLM systems for Replika's AI companion, shipping new features and the next generation of chat for millions of users.

• Developed multi-agent systems with Python, FastAPI, Redis, and RAG, focused on generating better conversations and chat experiences.
• In a high-agency two-person team, architected the backend and LLM integrations for a new high-growth AI chat and roleplay app.
• Helped validate the market from zero, acquiring thousands of users and a community in under three months.
• Leveraged models for text generation, image generation and recognition, extraction, formatting, and moderation.

Led the backend team part time on an AI fashion platform, owning architecture decisions and delivery across features and image generation.

• Guided backend execution across Python, Golang, and TypeScript services.
• Designed a multi-provider image-generation system combining internal GPU-hosted models with external APIs.
• Led development of the AI assistant that generates and iterates on clothing designs inside the platform.

Founding engineer. Built the core backend from scratch for an AI fashion design platform used by more than 100,000 designers.

• Developed serverless microservices for payments, webhooks, and message-queue processing; integrated Stripe and Auth0.
• Cut processing costs by 40% and improved client response times by 50% by refactoring the message consumer to Golang.
• Shipped new AI features with the AI and frontend teams across text and image workflows.
• Instrumented analytics tracking with Customer.io, Segment, Amplitude, and Intercom for growth and investor reporting.

Full-stack development of a B2B SaaS for data processing and analytics, spanning backend APIs, front-end features, and data engineering.

• Built backend APIs in Python and Flask and front-end features in HTML, JavaScript, and CSS, containerized with Docker on AWS and GCP.
• Designed and maintained ETL pipelines handling multi-TB weekly data flows with Kafka, NiFi, MongoDB, and Solr.
• Automated data workflows in Python, generated KPIs via Pentaho, and stored metrics in SQL for Power BI dashboards.

Built API connectors, ingestion workflows, and internal tooling for large-scale data pipelines.

• Built API connectors ingesting millions of JSON records into AWS S3 and managed EC2 instances.
• Automated repetitive tasks in Python, documented processes in Confluence, and worked in Scrum with JIRA.