Role Description We are seeking a Forward Deployed Engineer (FDE) with deep expertise in Google Cloud and applied AI to embed directly with our enterprise customers and turn frontier AI capabilities into production-grade systems. This role is for an engineer who thrives on ambiguity, codes alongside customer teams, and owns AI initiatives end-to-end — from technical discovery through architecture, build, deployment, and handoff. The ideal candidate has shipped agentic AI solutions on Google Cloud, is fluent in Vertex AI and Gemini, and is comfortable architecting multi-agent systems, RAG pipelines, and tool-calling integrations against messy enterprise environments. You will operate as an embedded builder — not an advisor — writing production code, debugging live systems, and co-developing with the customer’s engineering team to instill Google-grade engineering best practices and accelerate AI adoption. This position is remote and may require occasional travel. Role Responsibilities - Embed within customer engineering teams and lead technical discovery sessions with business stakeholders, engineering leadership, and security to translate ambiguous business problems into clear AI architectures and delivery plans. - Architect, code, and ship production-grade agentic AI solutions on Google Cloud — including multi-agent systems, MCP servers, sub-agents, skills, connectors, agentic wrappers, and safety guardrails — that move customers beyond pilots into measurable business value. - Design and implement Retrieval-Augmented Generation (RAG) pipelines and grounding architectures, including chunking strategy, vector databases, and embedding optimization to prevent hallucinations and ensure response quality. - Build the “connective tissue” between Google’s AI products and customer infrastructure, including APIs, legacy data silos, identity, and security perimeters. - Implement multi-agent patterns such as ReAct, self-reflection, and hierarchical delegation using frameworks like Google’s Agent Development Kit (ADK) or LangGraph. - Build high-performance evaluation pipelines and observability frameworks for agentic systems, with attention to accuracy, safety, latency, cost-per-request, and tokens-per-second. - Debug agent logic and optimize tool selection in live, high-traffic environments, including tracing conversation and request IDs across microservices to resolve production failures. - Co-build with customer engineering teams and act as a hands-on advocate for AI-assisted development, introducing and operationalizing AI coding tools to accelerate delivery and elevate engineering practices. - Drive a deliberate handoff to the customer’s team, ensuring long-term ownership, documentation, and end-user adoption after the engagement concludes. - Develop and maintain technical documentation, architecture decision records, and evaluation results across all assigned engagements. Qualifications - Bachelor’s degree in Engineering, Computer Science, a related field, or equivalent practical experience. - 5+ years of software development experience using Python, TypeScript, or comparable languages, with a track record of shipping production-grade code to external or internal customers. - Hands-on experience architecting and deploying AI systems on Google Cloud Platform (GCP), including: - Vertex AI — model deployment, fine-tuning workflows, evaluation, and platform-level observability. - Gemini models — prompt engineering, structured outputs, function/tool calling, and multimodal use cases. - BigQuery and Cloud Storage — as data and grounding sources for AI workloads. - Cloud Run, Cloud Functions, and Pub/Sub — for deploying and orchestrating agentic services. - Gemini Enterprise Agent Platform — designing, configuring, and deploying enterprise-grade agents, grounding on customer data sources, integrating tools and connectors. - Demonstrated experience building agentic and AI-driven solutions in production, including: - LLM application development — prompt engineering, agent development, and evaluation frameworks. - RAG architectures — vector databases, chunking strategy, and retrieval evaluation. - Data pipelines — structured and unstructured data ingestion to power enterprise-grade AI solutions. - Experience deploying cloud resources via Terraform or similar infrastructure-as-code tools. - Experience leading technical discovery sessions with business stakeholders and engineering teams to define AI requirements and translate ambiguous business goals into technical roadmaps. - Experience integrating AI systems with enterprise IT infrastructure, including authenticated APIs, legacy data systems, and corporate security perimeters. - Ability to travel up to 50% of the time to customer sites. - Outstanding communication skills, including the ability to explain complex AI and architectural concepts to both deep-technical engineers and non-technical executives. Nice to Have Qualifications - Master’s degree or PhD in AI, Computer Science, Machine Learning, or a related technical field. - Experience implementing multi-agent systems using frameworks such as Google’s Agent Development Kit (ADK), LangGraph, or CrewAI, and complex agent patterns including ReAct, self-reflection, and hierarchical delegation. - Hands-on experience designing and deploying Model Context Protocol (MCP) servers, tool-calling protocols, and connector ecosystems for agentic systems. - Knowledge of “LLM-native” operational metrics (tokens/sec, cost-per-request, time-to-first-token) and techniques for optimizing state management, granular tracing, and conversation-ID propagation across microservices. - Track record of troubleshooting live, high-traffic production AI systems during critical windows. - Experience architecting AI solutions within complex infrastructures, including data sovereignty, secure governance, and air-gapped or regulated environments. - Experience designing user-facing interfaces for AI and agentic systems with attention to context engineering, transparency, and explainability. - Experience driving organization-wide initiatives (e.g., migrations to new AI stacks, engineering-velocity programs) that deliver measurable improvements to engineering productivity and business outcomes. - Experience as an advocate for AI-assisted software development, including introducing AI coding assistants to enterprise engineering teams and developing internal best practices for their use. - Google Cloud certifications: - Google Cloud Professional Machine Learning Engineer - Google Cloud Professional Cloud Architect - Google Cloud Professional Data Engineer - Familiarity with full-stack application development and REST/GraphQL API design. Benefits - This is a full-time position based in Quebec, Canada. - Valtech offers a comprehensive benefits package effective after three months of continuous service: - A comprehensive insurance plan, where you can choose the module that best suits your needs—Gold, Silver, or Bronze. The employer may contribute up to 80% of your coverage depending on the selected module. This plan includes short- and long-term disability coverage. - Dialogue via Sun Life provides virtual healthcare services, allowing you to consult with a healthcare professional for emergencies, prescription renewals, and more. You also have access to the Employee and Family Assistance Program, as well as a complete mental health support program. - A $500 Personal Spending Account, which can be used for healthcare reimbursements, gym memberships, public transit passes, office supplies, or contributions to your RRSP through Valtech. - A retirement plan where Valtech will match 100% of your RRSP contributions through a Deferred Profit Sharing Plan (DPSP), up to a maximum of 4%. You can start contributing to your RRSP immediately, and to the DPSP after 3 months. The vesting of the DPSP will be after 24 months of service. - Access to flexible vacation under Valtech's policy to support your work-life balance, with 5 days available during your probation period and a prorated amount calculated for the remainder of the year. - Personal Technology Reimbursement – $30/month for every employee-offered on day 1. - We close during the winter holidays and offer flexible scheduling throughout the year, so you can enjoy those sunny Friday afternoons—provided your weekly hours are completed. Your Application Process Once you apply, our Talent Acquisition team will review your application. If your skills and experience align with the role, we’ll reach out for next steps. Your CV should cover key information on relevant experiences and expertise. We do not require information such as age, gender, marital status, or a headshot in your application. We review all candidates based on skills, experience, and potential. ⚠️ Beware of recruitment fraud: Only engage with official Valtech email addresses. We are committed to inclusion and accessibility. If you need reasonable accommodations during the interview process, please either indicate it in your application or let your Talent Partner know.