
Alexis
From France (UTC+2)
10 years of commercial experience
Lemon.io stats
Alexis – AWS, Python, LLM
Meet Alexis, a dynamic developer specializing in data engineering and machine learning. He excels at optimizing data pipelines and models for risk scoring and real-time predictions. Known for his effective communication skills and attention to detail, Alexis possesses an entrepreneurial spirit and strong technical expertise. He is dedicated to continuous learning and improvement, openly acknowledging past challenges and proactively seeking growth opportunities. With a talent for engaging with stakeholders, he fosters productive conversations and drives project success in startup environments.
Main technologies
Additional skills
Ready to start
april 22rdDirect hire
Potentially possibleReady to get matched with vetted developers fast?
Let’s get started today!Experience Highlights
AI Engineering freelancer
The product is an autonomous Customer Support Agent designed for expense management in businesses (B2B). It assists users with tasks such as retrieving information about user approvals, creating expense rules, and analyzing data.
- Designed the worflow to respond to the different use cases: data retrieval, analysis, and configurations;
- Implemented the system from scratch using LangGraph;
- Managed all prompts necessary, tailoring the information provided for each step (explanation of the business, relevant data schemas, etc.) while measuring the effectiveness of nodes separately;
- Developed an intermediate backend to be provided as tools for the agent. This backend would interact, in turn, with the main company backend;
- Deployed the backend on ec2 using Docker.
AI Engineering freelancer
Improved the client's internal AI usage by implementing a Retrieval Augmented Generation system that integrates the company's existing knowledge about customers and product development from their knowledge base, CRM, and internal database.
- Set up conversion of documents to embeddings using OpenAI's embeddings API;
- Stored vectors in superbase and set up vector similarity functionality;
- Pipelining for continuous integration of updated Knowledge Base and CRM;
- Built search with entity recognition to convert queries into embeddings for lookups;
- Lowered costs by storing all embeddings already obtained;
- Offered via API with options to choose the source of the augmented context: KB, CRM, or Data Warehouse.
Machine Learning Lead
The product is a platform for knowledge enthusiasts to discover and create quizzes. AI assists by helping users choose topics, set difficulty levels, and adjust question types, while also identifying engaging titles and hashtags. Its recommendation model personalizes quiz suggestions based on user preferences and promotes new content.
- Developed the recommending system using TensorFlow and exposed it through an API (in the style of "Tiktok's for you feed");
- Developed the Data pipelining to feed the recommender in real time;
- Set up and implemented the agentic workflow to assist quiz creation;
- Designed tests to ensure the factuality and diversity of our quizzes;
- Deployed everything on EC2, using FastAPI, Docker, and CI/CD;
- Managed all the infrastructure with Terraform;
- Implemented semantic search to find quizzes based on keywords;
- Ensured security and scalability of the backend, managing authentication, load balancing, and alerts.
Data Science Lead
The client is a startup that buys invoices from Chilean companies, which the recipients are to pay. Historically, invoice reviews have experienced a high rejection rate based on various risk factors. The project's goal was to develop a machine-learning model to evaluate these assets and generate risk-based proposals.
- Designed the proposed solution;
- Defined success metrics, identified risks, and aligned stakeholders;
- Led the development, assisted by a more junior data scientist;
- Developed data pipelines to feed the model using data;
- Deployed the solution on GCP to be called directly from the product.
Minute of glory:
- The machine learning model approach reduced the rejection rate by 10% in the first version and another 10% in the second iteration.