Full Stack AI Engineer

Full Stack AI Engineer

Role/Responsibilities:

Author precise feature specs covering requirements, edge cases, constraints, and acceptance criteria before any code is written or AI agent is invoked

Own features end-to-end — translating user outcomes into acceptance criteria, driving development through AI-assisted workflows, and validating output against the spec before delivery

Design and run generator-critic pipelines — using AI to generate output and a structured critique pass against the same spec to validate it, iterating until acceptance criteria are met

Build and maintain software components — APIs, data layers, services, and integrations — as the engineering foundation that AI-native workflows operate on top of

Evaluate and adopt AI tools with structured reasoning — assess new tooling against defined criteria, bring recommendations with evidence, and stay current with the evolving AI development landscape

Work autonomously across development, quality, and requirements — minimising handoffs through disciplined spec authorship, self-managed validation, and proactive flagging of gaps before building

 

Required Skills and Experience:

Bachelor's degree in software engineering, Computer Science, or a related technical field

5+ years of overall software development experience, with at least 3 years actively using AI tools as a core part of the development workflow

Proficiency in .NET, MS SQL Server (or equivalent RDBMS), MongoDB (or equivalent NoSQL), and API development

Ability to write structured, machine-precise specs that serve as ground truth for both code generation and output validation

Practical understanding of prompt construction, context engineering, and diagnosing AI output failures

Working awareness of the AI tool ecosystem — intelligent system tooling (LLM APIs, RAG, vector databases, agent frameworks) and SDLC acceleration tooling (agentic coding, AI code review, AI test generation)

Strong written communication skills and experience working in Agile or Kanban environments with end-to-end ownership of deliverables

 

Nice to Have Qualities & Skills

Hands-on experience building RAG pipelines, working with vector databases, or integrating LLM APIs into production systems

Experience with multi-agent orchestration frameworks such as LangChain, LangGraph, CrewAI, or AutoGen

Familiarity with AI observability tooling such as LangSmith, LangFuse, or Braintrust

Exposure to spec-driven development practices such as BMAD or GitHub Spec Kit

Exposure to real estate technology, mortgage, or related financial services domain

Awareness of Model Context Protocol (MCP) and its role in connecting AI agents to external tools and data sources