About the Role
We are looking for Full-stack engineer to design and develop AI-powered systems built on top of large language models. The main focus is on building intelligent agents, orchestrating multi-step model workflows, and integrating LLM capabilities into real-world products and business processes.
Full-time, remote
What You’ll Be Doing
Build backend services using Node.js and TypeScript to support AI-driven features and workflows
Contribute to frontend development (Vue 3) for AI product interfaces and full-stack features when needed
Design and implement AI agents with tool usage, memory, and context management
Integrate LLMs with external APIs, services, and enterprise systems
Improve model output quality through evaluation, testing, and observability practices
Contribute to system architecture decisions and evolution of AI infrastructure
Stay current with advancements in LLMs and apply new approaches to production systems
What We’re Looking For
Strong production experience with Node.js and Vue.js
Solid understanding of backend architecture and system design principles
Experience working with MongoDB or other NoSQL databases
Hands-on experience building AI agents (tool use, memory, context handling)
Strong knowledge of LangChain and/or LangGraph (JS/TS)
Experience implementing RAG pipelines and vector search systems
Understanding of agentic patterns (planning, retrieval, self-correction)
Familiarity with LLM evaluation and testing methodologies
Nice to Have
Experience with event-driven architectures (Kafka, NATS)
Experience with AWS (Lambda, S3, ECS, Bedrock, etc.)
Knowledge of Docker and Kubernetes
Experience with microservices architecture
Familiarity with MCP (Model Context Protocol)
Python experience in AI/ML contexts