AI Engineer

Location: UK, Brazil or Toronto (Remote/Hybrid) 
Reporting to:
Regional Development Manager 

Type: Full-Time, Permanent 
Start Date: ASAP 

About LemonEdge 

LemonEdge is a next-generation accounting platform built specifically for private capital markets. Our technology powers fund administrators, private equity firms, and asset managers with a flexible, scalable solution that automates complex calculations, enhances transparency, and accelerates operational efficiency. 

Since launch in 2020, we have grown to 75+ employees across six continents, backed by leading investors including Blackstone Strategic Innovations and Sidekick Partners. Our fund and portfolio accounting solution supports some of the most complex and largest global clients, with a combined asset base of over $1.4 trillion. 

Our culture prioritises speed, ownership, and collaboration. As a scaling business, you will join a fast-paced, entrepreneurial team with the opportunity to make a direct impact on our product, clients, and future growth. 

The Opportunity 

We are hiring an AI Engineer to drive our AI roadmap across a .NET-based platform moving to the web. You will own the end-to-end design and implementation of documentation-driven AI capabilities: sourcing and structuring knowledge, building secure NLP chat over our documentation and code, and introducing agentic workflows that integrate deeply with our products and services. This is a hands-on role, working closely with Engineering and Product to deliver secure, well-documented, and performant AI features that are production-ready for our global client base. 

Key Responsibilities 

• Define and evolve the AI roadmap, aligned with product, platform, and client needs. 

• Implement documentation ingestion pipelines (discover, structure, enrich, version). 

• Build secure, knowledge-based chat (eg. RAG) over internal and client documentation. 

• Collaborate with engineers to integrate AI capabilities into existing and new products. 

• Work with Engineering to support MCP-based tooling and AI-assisted workflows. 

• Design and implement agentic workflows that orchestrate multi-step tasks across services. 

• Ensure AI systems are secure, with robust data access controls and tenancy boundaries. 

• Establish performance, reliability, and observability standards for AI services in production. 

• Stay current with AI/LLM tooling and recommend pragmatic, value-focused improvements 

About You – Ideal Profile 

• 5–10 years in engineering, with 2+ years focused on applied AI/ML or LLM-based systems. 

• Strong background in
  .NET with experience in
  APIs, services, and background processing. 

• Hands-on experience with LLM platforms (eg. Azure OpenAI) and RAG-style solutions. 

• Familiarity with agent frameworks and orchestration patterns for multi-step workflows. 

• Comfortable working with web and cloud-native architectures (Azure preferred). 

• Solid understanding of enterprise security, data privacy, and tenancy considerations for AI. 

• Strong communicator, able to work cross-functionally with Product and Engineering teams. 

• Pragmatic, experiment-friendly, but adept in hardening prototypes for production. 

What Success Looks Like (KPIs & Metrics) 

• Documented AI roadmap with delivered, measurable milestones adopted. 

• High-quality documentation ingestion and knowledge base underpinning reliable chatbot. 

• Secure, performant AI features embedded in .NET product with positive user feedback. 

• Agentic workflows that reduce manual effort or improve speed/quality of key processes. 

• Internal adoption of AI tooling (including MCP integrations) by engineering teams. 

• Clear documentation, runbooks, and observability in place for all AI services in production. 

What We Offer 

• A central role
  in shaping the AI direction of a modern, globally used financial platform. 

• The chance to build foundational AI capabilities
  from the ground up. 

• Direct influence on product strategy, engineering standards, and platform architecture. 

• A collaborative environment with strong engineering talent and support from leadership. 

• Flexibility in remote/hybrid working, with autonomy to experiment and innovate. 

• Competitive compensation, equity, and benefits.