Description

In this role, you will shape the future of AI by building robust agent architectures and RAG pipelines while ensuring high reliability through sophisticated evaluation systems in an AWS environment.

Requirements

• •Excellent academic background in quantitative discipline
• •Current Bachelor’s or Master’s degree studies
• •First experiences with Cloud Infrastructure (AWS)
• •Hands on experience in Python
• •Knowledge in LLM frameworks, RAG and vector databases
• •Experience creating LLM-powered applications and agents
• •Experience with ML packages in Python
• •Curiosity and enthusiasm for AI technologies
• •Result-oriented and pragmatic working style
• •Fluency in English (written & spoken)
• •Provision of transcript and work references
• •Experience with AI Agent or RAG Evaluation Systems
• •Understanding of software engineering principles
• •Familiarity with end-to-end ML projects
• •Experience with Infrastructure as Code (Terraform) (plus)
• •Experience with CI/CD frameworks (plus)

Tasks

• •Enhance ML/LLMOps and AI agent infrastructure
• •Evaluate and implement LLM frameworks and architectures
• •Integrate various third-party APIs
• •Design AI agent evaluation systems
• •Measure reasoning quality, reliability, and consistency
• •Automate AI agent systems and RAG pipelines
• •Document findings in the internal knowledge base
• •Improve machine learning and data pipelines
• •Apply industry-critical infrastructure technologies productively

Tools & Technologies

Benefits