AI Engineer
What is the project idea?
We are looking for a talented AI Engineer specializing in LLM & Backend Integration/Development to join a fintech project. This is a position for a project focused on developing cutting edge fintech systems. You will be working on a platform that uses AI to provide intelligent insights and enhance the work environment on the fintech domain. You will integrate with a team of 2 AI Engineers and support both maintenance of existing systems and the development of new systems and implementing new business use-cases.
What is the team size and structure?
2 Senior AI Engineers and 1 Middle AI Engineer, PM, 2 Senior Back-end Engineers and 1 Middle Back-End Engineer.
How many stages of the interview are there?
— Interview with the Recruiter — up to 30 min.;
— Technical interview with Ralabs — up to 1 hour;
— Interview with the Client — up to 1 hour.
Requirements:
- At least 3 years of commercial experience as an AI Engineer or a similar role, preferably within the fintech industry;
- Strong proficiency in Python and hands-on experience on developing backend systems preferably with FastAPI;
- Experience with Large Language Models (LLMs) and integrating with APIs (e.g., OpenAI, Hugging Face);
- Proven experience working with frameworks like LangChain, LangGraph, LlamaIndex;
- Hands-on experience implementing RAG;
- Practical experience in designing and building agent-based AI systems;
- Solid knowledge of relational databases, specifically Postgres, including schema design;
- Experience with cloud platforms, preferably Azure;
- Experience in designing and implementing REST APIs;
- Good problem solving skills;
At least an Upper-Intermediate level of English.
Responsibilities:
- Develop and integrate LLM-powered features to provide users with personalized financial insights and support.
- Set up and maintain a secure and scalable FastAPI backend service.
- Design and extend the Postgres database schema to manage user data.
- Implement and extend secure chat session management, message history storage, and user profile payload integration.
- Deploy and manage the application on Azure, ensuring high availability and reliability.
- Occasional work on traditional ML systems based on project needs.