AI Engineer

We are looking for an experienced Senior AI Engineer who demonstrates a high level of autonomy in designing full-stack solutions and can make a tangible impact on the development of a flagship medical assistant used by millions of doctors worldwide. Our Client is an innovative organization that combines the stability of a mature company with the agility and culture of a startup. The project focuses on building a central Generative AI (GenAI) platform, enabling hundreds of product teams to create and deploy scalable AI agents. 📍 WORK MODE: 100% remote ⏱️ AVAILABILITY: We are looking for candidates available immediately or with a notice period of up to one month. 🧑‍💻 WHAT WILL YOU BE DOING? • Designing, building, and operating production-grade LLM (Large Language Model) systems and AI agents, ensuring the highest quality standards. • Implementing modern GenAI patterns such as RAG (Retrieval-Augmented Generation), routing, tool usage, and advanced agent orchestration. • Creating evaluation frameworks, including regression tests, A/B tests, and rubric-based qualitative assessments (e.g. ROUGE, BLEU). • Optimizing AI workloads for cost, latency, reliability, and minimizing hallucinations in mission-critical medical systems. • Implementing AI security and trust practices, including guardrails and system-level error mitigation. • Working closely with product, platform, and security teams to deliver end-to-end features. 🔍 WHAT WE EXPECT FROM YOU Must-have: • Minimum 8 years of professional experience in software engineering, with a strong focus on Python and backend technologies. • Hands-on experience deploying LLM-based applications or agents to production environments, and confidence in live coding interviews. • Knowledge of frameworks such as LangChain, LangGraph, or equivalent agent-building tools, as well as Pydantic for data validation. • Experience with RAG pipelines, vector search (e.g. OpenSearch), and monitoring systems (Tracing, Observability). • Ability to build secure and reliable cloud systems using AWS, Azure, or GCP (Google Cloud Platform). • Familiarity with CI/CD processes and Infrastructure as Code (IaC) practices. Nice-to-have: • Experience optimizing performance and cost for large-scale LLM workloads. • Background in regulated environments compliant with SOC 2 or HIPAA standards. • Knowledge of AI security best practices and AI ethics. 🤝 WHY JOIN? • Stable employment in a team of 100+ talented engineers. • Real impact on patients’ health and lives by building tools that reduce diagnostic errors. • International work environment with high autonomy and opportunities to mentor others. • Exposure to a cutting-edge technology stack in the Generative AI space. Thank you for all applications. We will contact selected candidates.