Forward Deployed Engineer (AI Practice)

Greenlight helps organizations solve complex business challenges through intelligent automation, agentic AI, and custom technology solutions.

Our teams work directly with clients to understand their operations, identify opportunities, and rapidly build solutions that create measurable business value. We combine deep consulting expertise with hands-on engineering to bridge the gap between strategy and execution.

We’re building a future where consultants and engineers work alongside AI to deliver faster outcomes, stronger businesses, and transformative customer experiences. Anthropic’s Claude is embedded across how we design, build, and validate solutions - and this role is at the technical frontier of that capability.

What makes a star at Greenlight?

· Builder's instinct, architect's discipline

· The most technically credible person in the room

· AI-native at depth - you know how LLMs fail and build around it

· Client-embedded, not arm's length

· Commercially aware - scope, economics, outcomes

The Role

The Forward Deployed Engineer is Greenlight’s most senior technical delivery role. You design, build, and operationalize AI agent workflows and intelligent automation solutions - embedded directly in client environments, working alongside their teams to deliver production-grade solutions that create measurable business outcomes.

This is not a back-office engineering role. You will be in client discovery sessions, presenting architectures to IT leadership, deploying AI agents against real enterprise systems, and building the reusable skills and accelerators that make Greenlight faster and more differentiated on every subsequent engagement. You are expected to be the most technically credible person in the room - combining deep AI fluency with the consulting presence of a senior practitioner.

You work at the frontier of agentic AI - designing and building Claude-powered solutions, connecting AI agents to enterprise systems through MCP integrations, and producing the technical documentation that the delivery team and the client can both stand behind. The platform is Anthropic Claude. The problem space is complex, regulated, and high-stakes. The bar is production-grade.

At a Glance

Reports To

AI Practice Lead

Works Closely With

Pre-Sales SE, Automation Business Consultant, AI Delivery Engagement Manager

Client Interaction

Yes — C-suite, IT architects, operations leaders, technical teams

Travel Requirement

Regular client travel required — discovery, workshops, POC delivery, go-live

Platform Focus

Anthropic Claude (Cowork + Skills), MCP, Python / Node.js, REST APIs

Seniority

Intermediate 3-5 year’s experience

Location

Onshore Canada — Toronto preferred

Engagement Type

Hybrid — onsite client-facing with remote delivery phases

What You’ll Do

Solution Architecture & Technical Discovery

• Lead technical discovery workshops with C-suite, IT architects, and operations leaders - identifying high-value AI automation opportunities and translating complex operational workflows into executable solution architectures
• Design end-to-end AI agent architectures using Anthropic’s Claude platform (Cowork and Skills framework), aligned to client infrastructure, security requirements, and compliance constraints
• Translate business requirements into agent-based automation blueprints: what the AI owns, what stays human, how exceptions route, and how the two coordinate
• Assess the right solution architecture for each use case - knowing when a Claude agent is the answer, when a procode integration is cleaner, and when a simpler rules-based approach is more appropriate than AI
• Present technical architectures to executive and non-technical audiences with clarity, confidence, and the credibility that comes from having built things like this before

AI Agent Build & Delivery

• Engineer production-ready AI agent workflows using Claude Cowork and the Skills framework - built to a standard that holds up in regulated, enterprise production environments
• Develop and configure Claude Skills: structured instruction sets, templates, validation rules, and reference documents that encode client-specific processes and quality standards into repeatable AI agent behaviour
• Build and maintain MCP connectors that integrate AI agents with enterprise systems - CRMs, ERPs, document management platforms, core banking systems, and custom APIs - handling authentication, data mapping, error handling, and audit requirements
• Implement advanced LLM patterns where required: retrieval-augmented generation (RAG), chain-of-thought reasoning, tool use, multi-agent orchestration, and structured output validation
• Conduct output validation, performance tuning, and safety testing of deployed AI agents before client go-live - quality is non-negotiable when outputs go to regulators or clients

Procode & Integration Engineering

• Write production-quality Python or Node.js to extend platform capability - data pipelines, transformation logic, webhook handlers, API wrappers, and back-end components that sit outside the automation itself
• Build, test, and maintain integrations with enterprise platform