Forward Deployed Engineer, Agentic Platform

About the role

This position involves building and deploying AI agents within the North platform to solve complex enterprise challenges. You will act as a technical bridge between Cohere and our clients, managing the full lifecycle of agentic workflows from initial concept to production. In this capacity, you will translate ambiguous business requirements into defined agentic workflows with clear evaluation metrics while designing and delivering LLM-powered agents capable of reasoning and executing tasks across APIs and enterprise data. You will develop and ship features for the North workspace platform throughout the entire product lifecycle and manage end-to-end use case scoping, including frontend development when necessary. Furthermore, you will establish shared engineering patterns to ensure consistent delivery across customer projects and own the full scope of a project to adapt to shifting priorities in a fast-paced environment.

Key facts

What you'll do

• Translate ambiguous business requirements into defined agentic workflows with clear evaluation metrics.
• Design and deliver LLM-powered agents capable of reasoning and executing tasks across APIs and enterprise data.
• Develop and ship features for the North workspace platform throughout the entire product lifecycle.
• Manage end-to-end use case scoping, including frontend development when necessary.
• Establish shared engineering patterns to ensure consistent delivery across customer projects.
• Travel 20 to 40 percent of the time to collaborate on-site with partners and clients.
• Conduct discovery sessions with enterprise stakeholders to clarify needs and constraints for agentic solutions.
• Implement robust testing strategies for agent behaviors to validate accuracy, safety, and performance in real-world scenarios.
• Collaborate closely with data science and product teams to iterate on agent designs based on empirical results.
• Optimize agent pipelines for latency and cost without compromising on capability or reliability.
• Document architectural decisions and operational procedures to support maintainability and scalability.
• Mentor junior engineers on best practices for building reliable and observable agentic systems.

Requirements

• Professional experience building and deploying production-grade software using Python.
• Demonstrated history of creating agentic applications and RAG systems, including multi-step task execution using ReAct or Plan-and-Execute patterns.
• Deep technical knowledge of the LLM stack, including frontier models, vector databases, and orchestration tools.
• Ability to design evaluation frameworks that measure agent accuracy, safety, and latency.
• Experience leading technical discussions with enterprise stakeholders to convert business needs into functional specifications.
• Ability to own the full scope of a project and adapt to shifting priorities in a fast-paced environment.
• Strong understanding of software engineering principles such as modularity, testing, and version control.
• Excellent written and verbal communication skills to articulate technical concepts to both technical and non-technical audiences.

Nice to have

• Experience defining architectural standards for AI systems across distributed teams.
• Background working within regulated industries such as healthcare, telecommunications, or finance.
• Familiarity with enterprise-level security, compliance, and auditability standards.

Skills & tools

• Python
• LLM orchestration frameworks
• Vector databases
• Frontend development (as needed)

Practical notes

• Benefits include 6 weeks of paid vacation, 100 percent parental leave top-up for up to 6 months, and health/dental coverage.
• Financial perks include a weekly lunch stipend, 401K/RRSP/pension matching, and annual enrichment credits for wellness, learning, and workspace improvements.
• Remote employees receive a 500 dollar home office stipend and a co-working benefit.
• Travel budget provided for visiting other offices and an annual company offsite.

This role is based in San Francisco with a remote-friendly policy, allowing for flexibility while maintaining close collaboration with the team. You will be expected to travel between 20 to 40 percent of the time to engage directly with partners and clients, ensuring alignment and trust through in-person interactions. The engagement is full-time, and the position sits within the Modeling team, where you will work alongside experts in large language models and agent systems. Compensation details are not specified in the source material, so specific figures regarding base salary, bonuses, or equity are not provided. The role emphasizes full lifecycle ownership, requiring you to manage tasks from initial discovery through deployment and optimization. You will need to be comfortable working in a dynamic environment where priorities can shift quickly and adaptability is essential. Strong Python skills are mandatory, as the majority of work will involve scripting, automation, and integration with various services. Experience with agentic patterns such as ReAct and Plan-and-Execute is explicitly required, indicating a focus on sophisticated reasoning and task execution capabilities. Deep familiarity with the LLM ecosystem, including models, vector stores, and orchestration frameworks, is necessary to design effective solutions. You will be responsible for building evaluation frameworks that assess multiple dimensions of agent performance, ensuring that deployed systems meet high standards of accuracy, safety, and responsiveness. Communication is a core component of the role, as you will regularly translate complex technical concepts into actionable insights for stakeholders with varying levels of expertise. The ability to lead technical discussions and convert business needs into functional specifications is critical for success. Ownership of the full project scope is expected, meaning you will see initiatives through from planning to execution while navigating evolving requirements. Shared engineering patterns will be developed to maintain consistency across client engagements, promoting best practices and scalability. When necessary, you will engage in frontend development to ensure end-to-end delivery of agentic workflows, even if your primary focus is on backend systems. Mentoring junior engineers and elevating the overall team's capabilities will be part of the role, requiring you to share knowledge and foster growth within the Modeling team. The nice to have section highlights the value of architectural leadership, especially in distributed team settings, as well as experience in regulated industries and enterprise security standards. These are not mandatory but are considered advantageous. Benefits are comprehensive and include generous vacation time, parental leave support, and health coverage, along with financial perks such as retirement matching and wellness stipends. Remote workers will receive specific support in the form of a home office stipend and co-working benefits, acknowledging the hybrid nature of the role. Travel budgets are provided to facilitate visits to offices and the annual company offsite, reinforcing the importance of in-person collaboration. Overall, this position is ideal for a Forward Deployed Engineer who thrives at the intersection of AI, software engineering, and client engagement, capable of driving agentic platforms from concept to production.