Create Alert
Email me similar jobs
Fullstack ai agent dev senior (node.js + vue.js + agent + rag) [remote from selected countries in the eu]
Seniority : Due to the nature of the position, we are looking for someone with at least 5+ years of experience in similar roles.
To be considered for the role, it is mandatory you to fulfill these requirements:
- Solid back-end development experience in Node.js applying clean code, design patterns, and SOLID principles.
- Proven experience building and maintaining RESTful, service-oriented, and event-driven APIs, including API versioning and contract management.
- Solid front-end development experience with Vue.js and its modern ecosystem (Composition API, state management, routing, HTML5, CSS3, JavaScript/TypeScript).
- Experience creating reusable component libraries, Design Systems, and working with UI components (e.g., PrimeVue, eCharts).
- Demonstrated production experience integrating LLM APIs (handling authentication, rate limits, timeouts, streaming, retries, and graceful degradation).
- Applied prompt engineering experience in product environments (system prompts, few-shot, structured JSON Schema outputs, scope/tone control).
- Hands-on experience with function calling/tool use, argument validation, and multi-step workflow orchestration (LangChain, OpenAI, Anthropic, Semantic Kernel, or equivalent).
- Proven experience building end-to-end RAG pipelines (ingestion, parsing, chunking strategies, embeddings, indexing, context assembly, and source citations).
- Hands-on experience with vector databases and semantic search (Azure AI Search preferred, MongoDB Atlas Vector Search, pgvector, Qdrant, Pinecone, or Weaviate).
- Experience with hybrid search (semantic + lexical/BM25), reranking, retrieval parameter tuning (top-k, thresholds, metadata filters), and access control filtering.
- Experience with document ingestion pipelines, incremental indexing, document versioning, and hallucination mitigation techniques.
- Solid knowledge of cloud-native and microservices architectures, containerization with Docker, and cloud infrastructure on Azure.
- Practical experience with database modeling and performance optimization in MongoDB, as well as caching and messaging using Redis.
- Knowledge of end-to-end security practices (OAuth2/OIDC, JWT, authorization controls, XSS/CSRF protection).
- Experience implementing automated testing (unit, integration, UI), observability (logging, metrics, tracing), and web accessibility standards (A11y).
- Experience evaluating LLM performance in production (prompt regression testing, latency/cost monitoring, response quality diagnosis).
Beyond technical knowledge, we also expect you to have a collaborative and team-oriented profile:
- Technical excellence and commitment to code quality, simplicity, and maintainability across the entire stack.
- High technical autonomy with the ability to lead complex demands end-to-end independently.
- Systemic vision to understand the platform-wide impact of back-end and front-end technical choices.
- Strong collaboration and communication skills to work closely with UX, QA, DevOps, Mobile, and cross-functional teams.
- Proactivity in identifying risks, technical debt, and usability/architectural improvements.
- Pragmatism regarding AI: understanding where LLMs add true product value versus where deterministic solutions are preferable.
- Comfort working with non-deterministic, probabilistic systems by defining objective quality and acceptance criteria.
- Ownership and responsibility over AI outcomes, ensuring precision, transparency of sources, and trust for the end user.
In this role, you will be primarily responsible for building, evolving, and scaling modern web applications, APIs, and production-grade LLM/RAG solutions within our Client's digital platform, taking full hands-on ownership across both back-end and front-end architectures.
In a typical week you will:
- Develop scalable, secure, resilient, and performant end-to-end solutions, from API design to front-end interfaces.
- Define and enforce technical standards across front-end and back-end stacks while collaborating with Tech Leaders, Architects, UX, QA, DevOps, and multidisciplinary squads.
- Integrate, orchestrate, evaluate, and deploy LLM-based capabilities into production with strict control over quality, cost, latency, and security.
- Design and build end-to-end RAG pipelines including ingestion, parsing, chunking, embedding generation, vector indexing, retrieval, hybrid search, and metadata filtering.
- Implement function calling, tool integration, multi-step workflow orchestration, state management, idempotency, and deterministic fallback strategies for AI workflows.
- Create modern Vue.js user interfaces tailored for AI experiences, featuring real-time token streaming, loading states, citation rendering, and user feedback collection.
- Implement access control at the retrieval layer to ensure tenant, user, and role-based data segregation.
- Write unit, integration, and UI tests while diagnosing performance bottlenecks, rendering issues, and technical debt.
- Monitor, evaluate, and optimize production LLM features, handling prompt regressions, hallucinations, retrieval quality, and model failure scenarios.
- Maintain clear technical documentation covering APIs, component architectures, prompt pipelines, RAG data sources, and system decisions.
Sign in
To continue your applicationor continue with email
By continuing you agree to our Terms & Privacy Policy.
Similar jobs
Show more
