Full Stack Engineer, AI Systems

Axe Recruiting; United States; Remote; USD 140,000 - 190,000; Full time

Job summary

Axe Recruiting partners with a well-funded AI applications company to build the product layer that turns agent capability into reliable workflows. The role spans frontend, backend and AI integration, with ownership from idea through production.

You will design agent workflows, blend LLMs with tools, and ensure dependable performance across multi-step interactions. Join a fast-moving team and collaborate with ML, backend and product colleagues to ship features that endure in real-world usage,

Qualifications

• Proven full stack experience across frontend and backend.
• Strong grasp of system design and API architecture.
• Experience with LLMs, RAG systems or AI-powered apps.
• Pragmatic, ownership-driven mindset in ambiguous problems.
• Ability to ship features from idea to production.
• Comfort in a fast-moving environment with evolving requirements.

Responsibilities

• Deliver features spanning frontend, backend and AI integration.
• Design agent workflows that plan, call tools, handle failures and recover across steps.
• Combine LLMs, memory and external tools into dependable systems.
• Build real-time AI interactions with streaming data and low latency.
• Improve reliability, observability and fallback paths across the stack.
• Collaborate with ML, backend and product teams to release features.

Skills

Full stack engineering

System design

API architecture

LLMs / AI integration

Pragmatic engineering

Ownership

Fast-paced environment

Job description

Build the product layer that turns agent capability into workflows people can rely on.

The Opportunity

Our client wants AI that does more than chat: it should carry a goal across sessions and finish the job. This engineer builds the layer that makes that usable. A well-funded AI applications company, backed by an established technology company in Southeast Asia and building for a global market, they are rebuilding everyday productivity software as AI-native products. The full stack seat covers frontend, backend and AI integration, with a specific charge: decide how agents run, what happens when they fail, how they recover, and how they keep delivering value over many steps. If you have shipped LLM features and want to own the whole path from idea to production, this is that job.

Role Snapshot

• Location: United States, United Kingdom, Europe (Ireland, Germany, Poland, Portugal, Spain, Sweden, Switzerland) or Asia (Singapore, South Korea, China)
• Work Model: Remote in most locations; hybrid in the UK, Zurich and Seoul
• Employment Type: Full-time
• Compensation: Competitive, shared on intro call
• Team: Engineering, AI systems

What You’ll Own

• Deliver product features that span the frontend, the backend and the AI integration behind them.
• Design agent workflows that plan, call tools, hit failures and recover over many steps.
• Combine LLMs, memory and external tools into systems that stay dependable in real-world conditions.
• Build real-time AI interactions that stream, show partial results and respect tight latency budgets.
• Strengthen reliability, observability and fallback paths throughout the system.
• Work with ML, backend and product colleagues to get features all the way to release.
• Keep iterating on what real usage and real failures show you.

What You Bring

• Strong full stack engineering experience covering both frontend and backend.
• A sound grasp of system design and API architecture.
• Experience with LLMs, RAG systems or AI-powered applications.
• Pragmatic engineering judgment when the problem is ambiguous.
• Real ownership, shown by taking features from idea through to production.
• Ease in a fast-moving environment where requirements keep evolving.

Why This Role

• Agent work with real stakes: multi-step workflows that have to finish reliably across tools and sessions.
• Pattern-setting scope: you define how LLMs, memory and external tools are integrated, and the rest of the product builds on it.
• A practical stack: Next.js, Python, Node.js, PyTorch, commercial and open-source LLMs, SQL and NoSQL, Kubernetes and Docker.
• A small, hands-on team and a short hiring process of three to four interviews with a quick answer.

Not the Right Fit If

• You want to stay on one side of the stack. This role spans frontend, backend and AI integration.
• You see LLM work as prompt-writing. The job is failure handling, fallbacks, latency and observability.
• You need stable requirements; these evolve with real usage.