AI Engineer
Build production generative AI systems and pipelines for Thunes' payments platform. Work in the AI engineering team to deliver stateful agents, multimodal reasoning, and secure deployment to cloud.
What you'll do
- Architect production-grade RAG workflows on cloud resources
- Implement multimodal pipelines for charts, graphs and tables
- Design adversarial tests to stress-test models for vulnerabilities
- Define quantitative evaluation metrics and validate model upgrades
- Containerise and deploy solutions via GitLab CI with observability
What they're looking for
- 5+ years total AI engineering experience with GenAI deployments
- Experience architecting on major clouds such as AWS or GCP
- Expertise with LangChain, LangGraph or LlamaIndex orchestration
- Proficiency in Python, Pydantic, and asynchronous REST APIs
- Hands-on experience with vector databases and retrieval engineering
Skills
Summary written by StartupJobs from the company's listing. The full listing is on the company's website.
This job comes from the career page of Thunes. We link straight to the source.