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