About the role
The engineer owns the AI layer of the product: architecture, agents, retrieval, evaluation, and production reliability. The employer wants someone who can ship production-ready AI with little supervision. The company is not named on the posting.
What you'll do
- Own the AI layer of the product: quality, reliability, performance, and continuous improvement.
- Define technical solutions and design architectures, then implement, evaluate, deploy, and optimise AI systems.
- Build AI agents, workflows, tool calling, structured outputs, state, and memory.
- Develop evaluation datasets, regression tests, and adversarial tests, and monitor production behaviour.
- Review, test, and validate code produced with Claude Code and OpenAI Codex.
Requirements
- Strong proficiency in Python and asynchronous services.
- Experience developing AI agents, workflows, tool calling, MCP, structured outputs, state, and memory.
- Solid understanding of retrieval-augmented generation, embeddings, retrieval, reranking, and source grounding.
- Hands-on experience with Amazon Bedrock and AgentCore.
- Experience with evaluation datasets and with prompt-injection prevention, access controls, and tenant isolation.
About Not named on the posting (OnlineJobs 1764121)
The employer is hiring an engineer to own the AI layer of its product, from architecture through evaluation, deployment, and monitoring.
AI Alerts shares third-party job opportunities for informational purposes only. We are not the employer and are not involved in the hiring process. Always verify the company and role through official channels before applying, and never pay to apply, train, onboard, process documents, or secure a job offer. Legitimate employers do not ask applicants for money. Read our Terms to learn more.