Python Developer

About the role

In this role, you'll design, implement, and deploy AI systems using LLMs, RAG, and foundation models to enhance our Process Collaboration Agent. Collaborating with the team, you'll write maintainable code, conduct experiments, and continuously improve performance. Stay on top of industry trends and integrate cutting-edge AI tools into our projects.

Requirements

• 3+ years of experience working with Python and production-ready applications
• Strong understanding of Machine Learning concepts and AI applications
• Experience with LLM APIs providers (OpenAI, Anthropic, etc.)
• Hands-on experience implementing RAG systems and vector databases
• Knowledge of agentic frameworks and workflows (like LlamaIndex)
• Awareness of the latest AI tools to accelerate development.
• Strong problem-solving skills and the ability to work in a collaborative environment
• Bachelor or advanced degree in Computer Science, Engineering, AI, or similar area
• Good written and spoken English

Nice to have:

• Experience with AWS services like Step Functions, DynamoDB, Lambdas
• Experience with FastAPI or similar frameworks for building high-performance APIs
• Understanding of distributed systems and how to design scalable AI solutions
• Experience with observability of LLM applications
• Understanding of asynchronous programming
• JavaScript/TypeScript knowledge
• Experience building and deploying AI systems in production environments
• Worked with an agile methodology (SCRUM, Kanban)
• Ability to mentor and guide junior team members on AI-related topics

Responsibilities

• Design, implement, and deploy complex AI systems using LLMs, RAG, and foundation models that enhance our Process Collaboration Agent
• Collaborate with the rest of the team by writing unit-tested, maintainable code and carrying out code reviews
• Implement and evaluate LLM applications, designing metrics and processes to continuously improve performance
• Have an experimental and methodical mindset to developing new features. When writing a white paper before starting the feature, how will you run experiments to prove that your approach is the best? Once we deploy a new feature, how will you test to know that it's working? How will you gather data to improve performance over time?
• Stay updated with industry trends to incorporate cutting-edge AI techniques and tools into our projects