Senior Backend AI (NodeJS) Engineer at MEDvidi

Worldwide

<h3>Description</h3> <p><strong>MEDvidi </strong>is looking for a <strong>Senior AI (Node.JS) Engineer</strong> to join our AI Automation team and lead the development of <strong>AI-driven integrations</strong> within our telemedicine platform.</p><p>In this role, you will design and scale backend systems that connect our core product with AI services to automate workflows for patients and healthcare providers. You will work on production-grade systems with a strong focus on reliability, security, and user experience, and see your solutions directly improve how thousands of people interact with our platform.</p> <h3>Requirements</h3> <ul><li><strong>8+ years of commercial backend development with Node.js</strong> in product companies (preferably SaaS), with a <strong>deep understanding of how complex backend systems work end-to-end</strong></li><li><strong>Extensive experience in designing backend architectures and technical solutions</strong>, including system decomposition, technology choices, scalability trade-offs, and long-term maintainability</li><li>Strong experience working in <strong>product environments and startup-style teams</strong>, with high ownership, fast iteration cycles, and responsibility for business impact</li><li><strong>Solid expertise in building scalable, high-performance backend systems and robust APIs</strong>, with a clear understanding of data flows, failure modes, and performance bottlenecks</li><li><strong>Hands-on experience integrating LLMs into real production systems</strong>, where reliability, predictability, and cost control were critical (not demos or pet projects)</li><li>Solid practical knowledge of <strong>RAG pipelines</strong>, including embeddings, vector databases, retrieval strategies, ranking approaches, and informed tuning of top_k, chunking, and relevance vs latency trade-offs <strong>will be a plus</strong>.</li><li>Experience designing and implementing <strong>LLM agents and multi-step AI workflows</strong>, preferably with <strong>LangGraph</strong>, or similar frameworks (AutoGen, SmolAgents, etc.)</li><li>Clear understanding of <strong>ReAct patterns</strong>, agent roles, orchestration logic, and agent–supervisor architectures, including when such approaches are justified</li><li>Strong <strong>prompt engineering skills with measurable quality improvements</strong>, including iteration based on evaluation metrics rather than intuition alone</li><li>Ability to work with <strong>structured LLM outputs (JSON/YAML)</strong>, applying validation, schema enforcement, and reliability techniques beyond prompt-only solutions</li><li>Hands-on experience with <strong>PostgreSQL</strong>, including database schema design, migrations, and basic performance optimization</li><li>Hands-on experience with <strong>AWS </strong>(cdk, lambda, gateway, elastiCache)</li><li>Good understanding of <strong>observability, monitoring, and debugging in production</strong> (Grafana, OpenSearch, or similar), with the ability to diagnose system-level issues</li><li>Strong engineering culture: <strong>testing, CI/CD, production reliability, and technical ownership</strong></li><li><strong>Product-oriented mindset</strong>, with the ability to see the full picture and build user-centered automation rather than isolated technical components</li><li><strong>Fluent Russian; English B2+</strong></li><li>Ability to work <strong>CET hours</strong>, <strong>located outside Belarus and Russia</strong>, <strong>B2B format</strong>, own equipment</li></ul><p><br/></p><p><strong>Nice to have:</strong></p><ul><li>Skilled in prompt engineering with measurable quality improvements (e.g., using AI Eval frameworks).</li></ul> <h3>Responsibilities</h3> <ul><li>Design and build backend architecture for AI-powered automation systems, focusing on performance, scalability, and resilience.</li><li>Integrate and scale LLM-based product features, working closely with AI engineers and product teams.</li><li>Implement and evolve agent-based systems (e.g., ReAct, supervisor-agent models), supporting complex decision-making flows.</li><li>Optimize Retrieval-Augmented Generation (RAG) pipelines and LLM context enrichment using structured and unstructured data.</li><li>Develop robust APIs for internal services and external integrations.</li><li>Ensure strong observability, monitoring, and alerting practices using tools like Grafana and OpenSearch.</li><li>Participate in code reviews, contribute to architecture discussions, and promote engineering excellence.</li><li>Maintain high-quality technical documentation for newly-designed systems and APIs to ensure clarity and knowledge sharing within the team.</li><li>Collaborate with cross-functional teams to align backend systems with product goals and user needs.</li></ul><p><br/></p><p><strong>Why Join MEDvidi:</strong></p><ul><li>A chance to contribute to a high-impact, product-driven company in the medical tech space.</li><li>Clear growth opportunities and a competitive compensation package.</li><li>Fully remote collaboration from any EU country under a B2B model.</li><li>Health insurance is available after the probation period.</li><li>Sports &amp; wellness compensation.</li><li>19 paid vacation days annually.</li><li>4 additional wellness days each year.</li><li>Paid sick leave for the first 5 working days.</li><li>Thoughtful gifts for key life events.</li><li>Personalized English lessons through Preply.</li></ul><p><br/></p><p><strong>Ready to make an impact? Send us your profile - let’s build something meaningful together.</strong></p>