FlowFuse Full Stack Developer (AI-focused)

Fullstack Engineer (AI-Focused)

Job Description

At FlowFuse, a Fullstack Engineer (AI-Focused) builds real product features and internal tooling that apply artificial intelligence to practical user and engineering problems. This role is for a strong fullstack engineer with deep, hands-on experience shipping AI-powered features to production.

This is not a research role. You will focus on applied AI: integrating large language models, embeddings, and automation into FlowFuse in a way that is reliable, observable, secure, and valuable to users. This role will be a foundational contributor to establishing FlowFuse's initial AI patterns, tooling, and best practices.

You will collaborate closely with Product, Design, and other engineers to identify high-impact AI use cases and deliver them end to end, while remaining a fullstack contributor across the platform.

A Fullstack Engineer (AI-Focused) is primarily responsible for:

• Applied AI Feature Development: Designing and building AI-powered features and tooling used by customers and internal teams.
• End-to-End Delivery: Owning fullstack solutions that include frontend, backend, and AI components.
• Capability Building: Establishing patterns, guardrails, and examples that other engineers can safely build on.
• Reliability and Safety: Ensuring AI features behave predictably in production, including fallback behavior and observability.
• Collaboration: Working closely with Product, Design, and Engineering peers to scope and deliver AI-driven solutions.
  
  

Core Tasks and Responsibilities:

• Integrate LLM APIs and AI services into FlowFuse features and tooling.
• Build backend services and frontend interfaces that support AI-powered workflows.
• Prototype, evaluate, and productionize AI features with clear scope and guardrails.
• Design for AI failure modes, latency, cost, and operational constraints.
• Ensure AI features align with privacy, security, and SOC 2 requirements.
• Share best practices and patterns for applied AI across the engineering team.
• Contribute to broader fullstack product work as priorities evolve.
  
  

What is the Fullstack Engineer (AI-Focused) not responsible for?

• Training or fine-tuning foundational models.
• Conducting academic or exploratory ML research.
• Owning company-wide AI strategy.
• Replacing sound engineering judgment with automation.
  
  

Skills

What a Fullstack Engineer (AI-Focused) brings to the table:

• Strong experience working across the full stack.
• Demonstrated experience shipping AI-powered features to production.
• Hands-on experience integrating LLM APIs into real systems.
• Familiarity with embeddings, vector search, or retrieval-augmented generation.
• Strong judgment around AI tradeoffs, failure modes, cost, and observability.
• Ability to design AI systems that others can safely extend.
• Experience shipping small, well-scoped changes incrementally.
• Comfort working in a remote, async-first environment across multiple time zones.
• Pragmatic use of AI tools to accelerate development and improve outcomes.
  
  

Hiring Plan

• Resume Review
  
  

Review resumes and relevant experience. Conducted by the hiring manager.

• Screening Call (15 minutes)
  
  

Initial screener focused on role fit, communication, and alignment with how FlowFuse works. Conducted by the hiring manager or recruiter.

• Engineering Manager Call (45 minutes)
  
  

A deeper alignment conversation covering FlowFuse's direction, applied AI use cases, how the team works, and expectations for this role.

• Take-Home Assignment (2–3 hours, unpaid)
  
  

Candidates choose one of the following options. Both are explicitly time-boxed to 2–3 hours:

• Option A: Build a small AI-powered feature or tool (for example: intelligent search, summarization, validation, or an assistant-style workflow) using an LLM API.
• Option B: Contribute a small, scoped AI-related pull request or prototype demonstrating applied AI integration in an existing codebase.
• Note: AI tools are explicitly allowed and encouraged where appropriate.

• Technical Interview (60 minutes)
  
  

Review the take-home work with 2–3 team members. The discussion focuses on problem understanding, AI design decisions and tradeoffs, system structure, reliability considerations, and how the solution would evolve over time rather than feature completeness. There will be explicit discussion of where AI was used, how it was used, and why those choices were made.

• Team Interview (45 minutes)
  
  

Conversation focused on collaboration, communication style, and working cross-functionally.

• Offer
  
  

Extend an offer to the selected candidate.