Applied AI Engineer

Role overview Build and operate AI features for a proactive mobile communication product designed to make everyday coordination and collaboration easier with little or no prompting. The role spans LLM-powered workflows, backend integrations, evaluation, and production reliability. You’ll work with engineering and product colleagues to bring useful AI capabilities into a consumer application.

Responsibilities - Implement and deploy AI features using language models, tool calling, and agent workflows. - Develop prompting, context handling, memory, and orchestration for multi-step tasks. - Build backend APIs and integrations connecting models to product features and external tools. - Create evaluations that measure task completion, response quality, and system reliability. - Use production logs and evaluation results to diagnose model behavior, tool failures, and workflow defects. - Improve latency, inference costs, and reliability, and collaborate on testing and releases.

Requirements - At least three years of software or machine learning engineering experience, including AI applications. - Strong Python skills and experience building production backend systems. - Hands-on experience with LLM APIs, prompting, tool use, and agent workflows. - Understanding of model capabilities and limitations, inference, and context management. - Experience evaluating AI outputs, debugging failures, and improving model-driven workflows. - Knowledge of APIs, databases, asynchronous processing, and distributed systems, plus production deployment and maintenance experience.

Nice to have - Experience with retrieval-augmented generation, embeddings, vector databases, or retrieval systems. - Familiarity with open-source models such as Llama or Qwen and inference tools such as vLLM. - Model fine-tuning experience with PyTorch or JAX. - Experience building consumer AI products, especially messaging or productivity applications.