Full Stack Engineer, AI Systems

Darwin Recruitment; California; On-site; USD 120,000 - 180,000; Full time

Job summary

Darwin Recruitment seeks a skilled Full Stack Engineer – AI Systems in California to develop AI-native applications at scale, combining frontend, backend, and AI integrations. You will design AI agent workflows, manage multi-step tasks, and ensure reliable operation in real-world environments.

The role involves integrating LLMs, memory systems, and external tools into production-grade software, with a focus on streaming interactions, low latency, and robust error handling.

Qualifications

• Proven track record in full stack software development across frontend and backend.
• Solid understanding of system design, architecture, and API development.
• Experience with large language models (LLMs), retrieval-augmented generation (RAG), or AI-powered apps.
• Familiarity with AI agent architectures and multi-step workflow execution.
• Ability to make pragmatic engineering decisions in evolving environments.
• Strong ownership, from design to production, in fast-paced teams.

Responsibilities

• Develop end-to-end product features across frontend, backend, and AI integrations.
• Design and implement AI agent workflows for multi-step tasks using external tools and robust recovery.
• Integrate LLMs, memory systems, and third-party tools into scalable apps.
• Build real-time AI interactions with streaming, partial results, and latency optimization.
• Improve reliability, observability, error handling, and fallbacks for AI-driven apps.
• Collaborate with ML, backend, and product teams to deliver features from concept to production.
• Monitor performance and user interactions to refine AI workflows.

Skills

Full stack

API design

LLMs

RAG

AI agents

Tool integration

Tools

Next.js

Python

Node.js

PyTorch

Docker

Kubernetes

Job description

Job Title: Full Stack Engineer – AI Systems

Location: California

Industry: Artificial Intelligence / Software Engineering

Overview of the Role

We are working with an innovative technology company developing AI-powered applications designed to simplify everyday tasks, improve productivity, and automate complex workflows.

They are looking to hire a Full Stack Engineer – AI Systems to help develop and scale intelligent software products that go beyond traditional conversational AI. The role focuses on building reliable, AI-native applications capable of managing multi-step tasks, maintaining context, integrating external tools, and delivering consistent results with minimal user intervention.

This is an opportunity to work at the intersection of full stack development, large language models (LLMs), and AI agent systems, taking features from initial concept through to production deployment.

Key Responsibilities

• Develop end-to-end product features across frontend, backend, and AI integrations.
• Design and implement AI agent workflows capable of planning, executing multi-step tasks, using external tools, and recovering from failures.
• Integrate LLMs, memory systems, and third-party tools into scalable applications that operate reliably in real-world environments.
• Build responsive, real-time AI interactions using streaming, partial results, and latency-optimisation techniques.
• Improve system reliability, observability, error handling, and fallback mechanisms across AI-driven applications.
• Collaborate closely with machine learning, backend engineering, and product teams to deliver features from concept to production.
• Monitor application performance and user interactions, continuously improving system behaviour based on real-world usage and identified failure points.
• Establish reusable architectures and engineering practices for integrating AI capabilities into production-grade software systems.

Candidate Profile

Essential Requirements

• Strong experience in full stack software engineering, with expertise across frontend and backend development.
• Solid understanding of system design, software architecture, and API development.
• Experience working with large language models (LLMs), retrieval-augmented generation (RAG), or AI-powered applications.
• Understanding of AI agent architectures, tool integration, and multi-step workflow execution.
• Ability to make pragmatic engineering decisions in ambiguous and rapidly evolving environments.
• Strong sense of ownership, with the ability to take features from initial design through to production.
• Comfortable working in a fast-paced engineering environment where requirements evolve and solutions require continuous iteration.

Technical Skills

Experience with some or all of the following technologies:

• Frontend: Next.js
• Backend: Python, Node.js
• AI / Machine Learning: PyTorch, OpenAI, Anthropic, and open-source LLMs
• Databases: SQL and NoSQL
• Infrastructure: Kubernetes and Docker

Key Objectives

In this role, you will be responsible for:

• Delivering AI-powered product features that support persistent, goal-oriented workflows rather than simple conversational interactions.
• Designing and deploying AI agent systems capable of completing complex tasks across multiple tools and sessions.
• Optimising AI application latency and responsiveness without compromising output quality.
• Developing robust error-handling, fallback, and recovery mechanisms for LLMs and external tool integrations.
• Improving the reliability and success rate of AI workflows through testing, evaluation, monitoring, and continuous optimisation.
• Establishing scalable software architectures and reusable patterns for integrating LLMs, memory, and external tools.
• Contributing to intuitive, dependable AI applications that provide consistent value to users over time.

Working Environment

You will join a small, highly skilled engineering team working in a collaborative and hands-on environment. The team values technical excellence, independent thinking, rapid execution, and continuous learning.

This role offers the opportunity to take significant ownership of technical decisions, contribute directly to product development, and help shape the architecture of emerging AI-powered applications.