Senior FullStack engineer (AI-First)

About Fulcrum: We’re a team of tech-savvy, creative & passionate IT professionals. We’ve created a vibrant and performance-driven culture for ourselves where everyone is free to think & act outside the box. There are literally no limits to what you can do here, as long as we WOW our clients and OVER deliver what we promise.

Our client is a UK-based product company working on an AI-driven platform that acts as a personal assistant capable of interacting with users and integrating with external tools such as email and other services.

The product is currently being built from scratch in an R&D environment with a strong focus on AI agents, rapid prototyping, and fast iteration.

We are looking for a Full-Stack Engineer (AI-First) who will help build the MVP and shape the technical foundation of the product.

The role combines full-stack development with AI-driven workflows. The engineer will design and implement core product functionality, integrate LLM-based capabilities, and orchestrate AI-driven pipelines.

The position requires a high level of ownership and comfort working in a fast-paced startup environment



Team composition - Product Owner, Full-Stack Engineer, Designer and QA

Key Responsibilities

- Design and develop core product functionality for an AI-powered platform with autonomous agents
- Build and improve the agent runtime that allows AI agents to execute tasks, interact with tools, and run in isolated environments
- Develop chat-based and conversational interfaces that enable users to interact naturally with their AI agents
- Implement and evolve the memory system that allows agents to learn from conversations and store long-term context
- Design and build APIs and backend services powering agents, integrations, and real-time features
- Work with vector databases and RAG pipelines to support intelligent retrieval and context building
- Build real-time experiences (streaming responses, live updates) for interactive agent execution
- Participate in building the multi-agent orchestration layer, enabling collaboration between multiple AI agents
- Contribute to the AI tool ecosystem, integrating external services and building extensible agent skills
- Collaborate with product, design, and engineering teams to iterate quickly and deliver new features