Senior Forward Deployed Engineer

Greenlight Consulting; Toronto; Hybrid; CAD 110,000 - 150,000; Full time

Job summary

Greenlight Consulting in Toronto, ON is seeking a Senior Forward Deployed Engineer to design, build, and operationalize AI agent workflows embedded directly in client environments, delivering production-grade solutions that drive measurable business outcomes. The role requires 5+ years of full-stack experience and at least 1 year of forward-deployed delivery with Claude.

You will work across solution architecture, AI agent builds, and full-stack integration, collaborating with C-suite and IT

Qualifications

• 5+ years of professional full-stack or backend engineering experience.
• 1+ year of forward deployed, client-embedded, or consulting engineering experience.
• Hands-on experience building with LLM platforms in production — Anthropic Claude preferred; OpenAI, Azure OpenAI, or Gemini also relevant.

Responsibilities

• 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 the Skills framework), aligned to client infrastructure, security requirements, and compliance constraints
• Present technical architectures to executive and non-technical audiences with clarity and confidence
• 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 simpler is better than AI
• Engineer production-grade AI agent workflows using Claude Cowork and the Skills framework, built to a standard that holds up in regulated, enterprise production environments
• Build and maintain MCP connectors integrating AI agents with enterprise systems — CRMs, ERPs, document platforms, core banking systems, and custom APIs
• Implement advanced LLM patterns: RAG, tool use, multi-agent orchestration, structured output validation, and chain-of-thought reasoning
• Conduct output validation, performance tuning, and safety testing of deployed AI agents before client go-live
• Write production-quality Python and/or Node.js to extend platform capability
• Build, test, and maintain integrations with enterprise platforms (Salesforce, SharePoint, ServiceNow, Jira, DocuSign, and others) using REST, GraphQL, OAuth 2.0, and enterprise authentication patterns
• Design and implement monitoring, logging, and observability into deployed solutions
• Apply cloud platform fundamentals (AWS, Azure, or GCP) to deployment, scaling, and infrastructure decisions
• Build and continuously refine reusable Skills libraries, automation templates, and reference architectures
• Contribute to pre-sales activities: technical demos, POC builds, RFP responses, and solution estimations
• Produce high-quality technical documentation — solution design documents, architecture diagrams, runbooks, and post-deployment reports
• Mentor junior FDEs and Automation Engineers on AI agent patterns, LLM integration best practices, and platform capabilities
• You've been the most technical person in a client meeting and the most client-facing person in an engineering room
• You build things that work in production, not just in demos
• You define structure where none exists and deliver without hand-holding
• You write code the next engineer can understand
• You know when the LLM is going to fail before it does, and you've already built the fallback
• You leave every engagement with a client technical team more capable than when you arrived
• Complex, high-stakes enterprise AI projects that push you technically and strategically
• A team that combines deep consulting expertise with hands-on engineering
• Training budget and dedicated time for certifications
• Clear growth paths — technical track or leadership track
• Real work-life balance: hybrid model, flexible hours, and a culture that respects what matters outside of work
• A firm where your opinions on architecture, practice, and client strategy are actually heard

Skills

Full-stack engineering

Client-embedded delivery

LLM production experience

Cloud platforms (AWS/Azure/GCP)

Tools

Python

Node.js

REST APIs

GraphQL

TypeScript

SQL/NoSQL

Claude API

MCP connectors

LangSmith

OAuth 2.0

Job description

Greenlight helps organizations solve complex business challenges through intelligent automation, agentic AI, and custom technology solutions. We combine deep consulting expertise with hands‑on engineering to bridge the gap between strategy and execution. Anthropic's Claude is embedded across how we design, build, and validate solutions — and this role is at the technical frontier of that capability.

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
• Seniority: Senior — 5+ years full-stack engineering, 1+ year FDE or client-embedded delivery
• Platform Focus: Anthropic Claude (Cowork + Skills), MCP, Python / Node.js, REST APIs
• Travel: Regular client travel — discovery, workshops, POC delivery, go-live
• Location: Toronto, ON preferred — hybrid onsite + remote delivery
• Compensation: $110,000 – $150,000 CAD annually, based on experience

What Makes a Star at Greenlight

• Full-stack engineering foundation — you've built things end to end, backend to frontend, and you own the whole stack
• Builder's instinct, architect's discipline — working software over slide decks, every time
• AI‑native at depth — you know how LLMs fail and build reliable systems around them
• Client‑embedded, not arm's length — you thrive in client environments, not back-office settings
• Commercially aware — scope, delivery economics, and what it costs when technical decisions go sideways
• The most technically credible person in the room — credible with a CTO and a COO in the same meeting

The Role

The Senior 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.

You bring a strong full‑stack engineering background (5+ years) combined with at least one year of forward deployed or client‑embedded delivery experience. You know how to ship production‑grade software, navigate a complex enterprise environment, and show up credibly in front of technical and business stakeholders in the same day. The platform is Anthropic Claude. The problem space is complex, regulated, and high‑stakes. The bar is production‑grade.

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
• Present technical architectures to executive and non‑technical audiences with clarity, confidence, and the credibility that comes from having built things like this before
• 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 simpler is better than AI

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
• Build and maintain MCP connectors integrating AI agents with enterprise systems — CRMs, ERPs, document platforms, core banking systems, and custom APIs — handling authentication, data mapping, error handling, and audit requirements
• Implement advanced LLM patterns: RAG, tool use, multi‑agent orchestration, structured output validation, and chain‑of‑thought reasoning
• Conduct output validation, performance tuning, and safety testing of deployed AI agents before client go‑live

Full-Stack & Integration Engineering

• Write production‑quality Python and/or Node.js to extend platform capability — data pipelines, transformation logic, webhook handlers, API wrappers, and back‑end components
• Build, test, and maintain integrations with enterprise platforms (Salesforce, SharePoint, ServiceNow, Jira, DocuSign, and others) using REST, GraphQL, OAuth 2.0, and enterprise authentication patterns
• Design and implement monitoring, logging, and observability into deployed solutions so operations teams can diagnose issues without requiring an engineer in the room
• Apply cloud platform fundamentals (AWS, Azure, or GCP) to deployment, scaling, and infrastructure decisions

Accelerators & Practice Development

• Build and continuously refine reusable Skills libraries, automation templates, and reference architectures that make every subsequent Greenlight engagement faster
• Contribute to pre‑sales activities: technical demos, POC builds, RFP responses, and solution estimations
• Produce high‑quality technical documentation — solution design documents, architecture diagrams, runbooks, and post‑deployment reports — written to a standard the client's IT team can maintain
• Mentor junior FDEs and Automation Engineers on AI agent patterns, LLM integration best practices, and platform capabilities

What We're Looking For

Experience

• 5+ years of professional full‑stack or backend engineering experience — building, shipping, and maintaining production systems
• 1+ year of forward deployed, client‑embedded, or consulting engineering experience — working directly inside client environments, not just delivering remotely
• Hands‑on experience building with LLM platforms in production — Anthropic Claude preferred; OpenAI, Azure OpenAI, or Gemini also relevant
• Demonstrated experience with enterprise system integrations — REST APIs, OAuth 2.0, webhooks, authentication flows at scale
• Experience deploying and maintaining solutions in cloud environments (AWS, Azure, or GCP)

Technical Stack

• Full‑Stack Engineering: Python and/or Node.js (production‑grade); REST & GraphQL APIs; TypeScript; SQL and NoSQL databases; CI/CD AI & LLM Anthropic Claude API; MCP connector design; RAG; multi‑agent orchestration; tool use; structured output validation; LLM evals & observability (LangSmith or equivalent)
• Enterprise Integration: Salesforce, SharePoint, ServiceNow, Jira, or similar; OAuth 2.0; webhook handling; error handling and retry logic at scale
• Cloud & DevOps: AWS, Azure, or GCP; Docker; deployment basics; logging and monitoring

What Makes You the Right Fit

• You've been the most technical person in a client meeting and the most client‑facing person in an engineering room — and you're comfortable in both
• You build things that work in production, not just in demos — and you know the difference
• You define structure where none exists and deliver without needing hand‑holding
• You write code the next engineer can understand without a two‑hour briefing
• You know when the LLM is going to fail before it does, and you've already built the fallback
• You leave every engagement with a client technical team more capable than when you arrived

What You'll Find at Greenlight

• Complex, high‑stakes enterprise AI projects that push you technically and strategically
• A team that combines deep consulting expertise with hands‑on engineering — no arm's‑length delivery
• Training budget and dedicated time for certifications
• Clear growth paths — technical track or leadership track
• Real work‑life balance: hybrid model, flexible hours, and a culture that respects what matters outside of work
• A firm where your opinions on architecture, practice, and client strategy are actually heard

We use AI tools to support parts of our recruitment — organizing applications and flagging relevant experience. These tools inform our process, they don't drive it. Every hiring decision is made by our team, full stop. We welcome applicants of all backgrounds. If you need accommodations during the process, please let us know.

Compensation

The expected salary range for this role is $120,000 – $140,000 CAD annually, based on experience and qualifications.