Developer AI Agent

Skills

About the Role

You will design, build, and operate long-running AI agent services in production. You will develop agent loops and tool-calling integrations, implement safety and permission controls, build RAG-based memory and knowledge systems, and own evaluation, tracing, observability, and regression testing. You will also engineer context management, long-session reliability, and cost controls.

Requirements

• 3–5 years of software engineering experience, including building LLM-based applications or agents
• University degree in Computer Science, Software Engineering, or a related discipline
• Production-quality coding experience in Python, TypeScript, Rust, or similar languages
• Familiarity with Linux environments
• Experience shipping agentic systems using tool calling and multi-step agent loops
• Knowledge of LLM security risks, including prompt injection and data exfiltration
• Experience with retrieval systems, vector databases, embeddings, and RAG
• Experience with LLM evaluation and tracing tooling such as Langfuse, LangSmith, or OpenTelemetry
• Ability to own reliability, scalability, cost efficiency, and maintainability
• Strong interest in financial markets and blockchain technologies

Responsibilities

• Design, build, and operate long-running production agent services
• Build agent loops and tool-calling integrations using frontier models
• Design agent safety, permission controls, and prompt injection protection
• Build agent memory and knowledge systems using RAG, knowledge graphs, and embeddings
• Own agent evaluation, tracing, observability, and regression testing
• Engineer context management, long-session reliability, and cost controls