תיאור המשרה
Description Popai is on a mission to transform the millions of conversations that happen between care teams and patients every day. We’re building the AI platform that turns every patient interaction into action - helping care teams understand what patients need, close gaps in care, and reach the people who need them most. Our goal is simple but ambitious: make he As an AI Engineer at Popai, you will design, build, and deploy intelligent systems that power our core product. You will work across the entire lifecycle—from building robust data pipelines for medical records and audio data to operationalizing cutting-edge LLMs and agentic workflows in production. What You'll Do Build AI & Data Pipelines: Design, build, and maintain data and AI pipelines that ingest, process, and analyze large-scale healthcare data (including medical records, audio signals, and system traffic). Develop Intelligent Systems: Build systems that extract structured entities, definitions, and actionable insights from complex unstructured data. Deploy AI Agents: Operationalize and integrate AI agents using LLMs, open-weight models, and specialized tools into production systems to automate reasoning and care workflows. Optimize Performance: Optimize model performance, inference pipelines, and latency to ensure high scalability and efficiency. Ensure Data Quality & Observability: Design reliable data workflows with built-in quality checks, consistency, and monitoring across all pipeline stages. R&D & Innovation: Experiment with emerging AI frameworks, model architectures, and agentic workflows to continuously elevate the platform's intelligence. Requirements What We're Looking For Experience: 6+ years of hands-on experience as a Software Engineer, AI Engineer, or Data Engineer. Scalability & Systems: Proven track record of working on high-scale, distributed systems with a focus on performance optimization and resilience. Data Infrastructure: Solid understanding of data processing and storage technologies (e.g., PostgreSQL, BigQuery, Snowflake, Spark, Kafka). AI & LLM Deployment: Practical experience integrating, serving, or fine-tuning LLMs and smaller specialized models (API-based or open-weight). Cloud & DevOps: Proficiency with cloud platforms (AWS, GCP, or Azure) and containerized setups (Docker, Kubernetes). Nice to Have Experience with LLM serving optimizations, quantization, prompt engineering, or agent orchestration frameworks (e.g., LangChain, LangGraph). Familiarity with audio/speech processing or medical record data systems. Experience designing event-driven, streaming architectures. Background in real-time inference or low-latency AI applications.