Python Full Stack Developer(with AILLM Integration Focus)

As a member of our team you will dive head-first into creating innovative solutions that advance businesses and careers. You will join an inspiring and curious team of technologists dedicated to improving the design development and delivery of high-quality software and AI-powered products.

We primarily manage several types of projects for clients across different countries and regions. As we grow quickly we are looking for a Python Full Stack Developer who is experienced in integrating AI and LLM capabilities into real-world applications. You will work closely with our Pre-Sales team to rapidly build Proof-of-Concept (POC) solutions that demonstrate our AI capabilities to prospective clients directly supporting our ability to win new business.

This is a highly autonomous role. You will take full ownership of your deliverables from technical design through delivery with minimal supervision. The ideal candidate is a resourceful self-driven developer who knows how to leverage modern AI tools and coding assistants to move fast without sacrificing quality.

Job Responsibilities:

• Design develop and deliver full-stack Python applications (backend) with React or similar frontend frameworks integrating LLM and AI agent capabilities to solve real client problems
• Collaborate closely with the Pre-Sales team to rapidly prototype and build compelling POCs that showcase AI-powered solutions directly contributing to new customer acquisition
• Integrate LLMs AI agents and automation pipelines (using tools such as LangChain LlamaIndex CrewAI or similar frameworks) into functional application features
• Build and maintain reusable AI components and accelerators that enable faster delivery and consistent quality across multiple client engagements
• Develop and maintain AI demo environments specifically designed for client presentations and capability showcasing
• Support the Pre-Sales department with effort estimates architecture blueprints and technical documentation; participate in client-facing meetings to explain AI solution benefits in clear business-friendly terms
• Stay current with rapidly evolving AI tools models and frameworks proactively adopting new solutions (such as OpenAI Anthropic Claude Google Gemini or open-source alternatives) to accelerate development
• Leverage AI-assisted coding tools (GitHub Copilot Cursor or similar) to maximize development velocity and maintain high output quality
• Work independently with a high degree of autonomy while maintaining strong collaboration with cross-functional teams and accountability in project delivery
• Ensure full compliance with corporate tools (Jira Confluence Time Management) processes and documentation requirements.

• 8 years of professional experience in software development with strong Python full-stack skills
• Proven experience building full-stack applications: Python backend (FastAPI Flask or Django) and React (or other modern JS frameworks) frontend
• Hands-on experience integrating LLMs and/or AI agents into production or demo applications. e.g. chatbots AI assistants intelligent automation or RAG-based solutions
• Familiarity with at least 2-3 major LLM platforms or APIs (OpenAI GPT Anthropic Claude Google Gemini or similar)
• Experience with AI/LLM orchestration frameworks such as LangChain LlamaIndex CrewAI AutoGen or equivalent
• Ability to work autonomously and move quickly comfortable making technical decisions independently and delivering with minimal oversight
• Experience with cloud platforms (Azure AWS or GCP) for deploying and hosting AI-powered applications
• Proficiency in development tools including Git/GitLab VS Code and standard CI/CD practices
• Strong communication skills in English able to explain technical concepts clearly to non-technical stakeholders and participate in client-facing pre-sales activities
• Experience using AI coding assistants (Copilot Cursor etc.) to accelerate development this is expected and valued.

• Experience with vector databases and RAG pipelines (e.g. Pinecone Weaviate Chroma pgvector) for grounding LLM outputs on enterprise data
• Exposure to pre-sales or client-facing consulting environments
• Familiarity with AI agent frameworks and multi-agent orchestration patterns
• Experience with containerization (Docker Kubernetes) for scalable application deployment.

• A dynamic and multinational environment with dedicated professionals who are ready to share their knowledge with you;
• Soft skills and technical training for current and emerging products and technologies;
• Career development: opportunity to grow within the team;
• Special referral bonuses for recommending your friends;
• Private Medical subscription;
• Meal tickets;
• Extra vacation days;
• Flexible working hours and work from home aligned with project needs;
• Friendly team who is eager to meet you.

We are the Stefanini group a global tech consulting company of Brazilian origin that believes in the power of people to transform businesses through technology.

We are present in over 40 countries and operate with the purpose of co-creating solutions TOGETHER WITH OUR CLIENTS that accelerate results and improve the experience of people and organizations.

Here we like to say that technology is not the end but the means: what really matters are the people who drive it all.

Our mindset is AI First meaning we invest in cutting-edge technology in everything we do focusing on results for our clients.

We are a company A GROUP that breathes collaboration and offers a dynamic environment where you will learn by doing grow alongside the team and have space to contribute with ideas and projects.

More than just talking about digital transformation we believe in real transformation that starts with people and impacts real businesses.

If you are looking for a place to develop innovate and be part of something bigger the Stefanini Group is your place.