Full Stack Engineer – AI Systems
DeepRec.ai · United Kingdom
About this role
The candidate will build the product layer that converts model capability into production-grade workflows for a proactive AI assistant. Responsibilities include building end-to-end features across frontend, backend, and AI integrations, and designing agent workflows for multi-step tasks. The technical environment involves working with Next.js, Python, Node.js, PyTorch, and various LLMs like OpenAI and Anthropic. The role requires improving reliability, observability, and fallback mechanisms in production. The engineer will work closely with ML, backend, and product teams in a small, high-talent-density team.
Skills & technologies
Read full description
Full Stack Engineer – AI Systems (Remote, Europe)
We're building a proactive AI assistant for everyday life — bringing intelligence to conversations, tasks, errands and workflows, with minimal prompting from the user. The goal: cut the time people spend on daily admin by up to 90%, with an assistant that reliably completes multi-step, real-world tasks rather than just chatting.
We're looking for a Full Stack Engineer – AI Systems to build the product layer that turns model capability into dependable, production-grade workflows — designing how our agents plan, act, fail, recover, and deliver consistent value to users.
What you'll be doing:
- Building end-to-end product features across frontend, backend, and AI integrations
- Designing agent workflows that handle planning, tool use, failure and recovery across multi-step tasks
- Integrating LLMs, memory, and external tools into systems that hold up under real-world, non-deterministic conditions
- Designing real-time AI interactions with streaming, partial results and tight latency constraints
- Improving reliability, observability and fallback mechanisms in production
- Working closely with ML, backend and product teams to ship end-to-end, and iterating fast on real usage data
What we're looking for:
- Strong full stack experience (frontend + backend)
- Solid grounding in system design and API architecture
- Experience with LLMs, RAG systems, or AI-powered applications in production
- Comfort with ambiguity and pragmatic decision-making
- Real ownership — taking features from idea through to shipped product
- Thrives in a fast-moving, high-autonomy environment
Stack: Next.js, Python, Node.js, PyTorch, OpenAI/Anthropic/open-source LLMs, SQL & NoSQL, Kubernetes, Docker
Set-up: UK-based team, hiring remotely across Europe. Small, high-talent-density team — decisions made collectively, work shipped fast, judgement and independence expected from day one.
Process: Straightforward — no more than 3–4 interviews, prompt decisions, no drawn-out process.
