Forward Deployed Engineer, Agentic Platform

About the Role

This position represents a distinctive chance to influence how businesses integrate artificial intelligence in practical scenarios. Acting as a liaison between our core North product and client engineering teams, you will tackle intricate challenges by securely embedding AI into vital sectors such as finance, healthcare, and telecommunications.

We seek software engineers specialized in applied AI to oversee the full lifecycle of agentic workflows driven by Large Language Models (LLMs). From initial prototypes to robust, enterprise-ready AI agents, your work will focus on delivering tangible business benefits within corporate workflows. Collaboration with customers will be key as you create pioneering agent workflows combining LLMs with tools, APIs, and data sources. Our pace mirrors that of a startup, but our standards align with enterprise demands — agents must be dependable, transparent, secure, and auditable from the outset.

Key Responsibilities

• Collaborate closely with enterprise clients to convert complex and uncertain business challenges into clearly defined agentic workflows featuring measurable success criteria and evaluation methods.
• Lead the architecture, development, and deployment of LLM-driven agents capable of reasoning, planning, and acting through integration with tools, APIs, and sensitive enterprise data, ensuring enterprise-grade reliability and efficiency.
• Develop and deliver features for North, our AI workspace platform, spanning the entire product lifecycle from ideation to production.
• Take full ownership over use case scoping and solution design, adapting flexibly across technical domains—including frontend development—to implement optimal solutions.
• Contribute to the development of shared frameworks and best practices that promote consistent, high-quality delivery across teams and projects.
• Provide clarity in ambiguous situations, foster consensus, and elevate engineering standards organization-wide.
• Be prepared for business travel up to 20–40% to engage directly on-site with customers and partners.

Required Qualifications

• Proven experience developing and deploying production-grade software using Python, emphasizing clean, testable, observable, and scalable coding practices.
• Demonstrated success building highly performant Retrieval-Augmented Generation (RAG) and agentic applications, including agents that plan and execute complex, multi-step workflows using techniques such as ReAct or Plan-and-Execute.
• In-depth knowledge of the LLM ecosystem, including frontier models, vector databases, and orchestration frameworks.
• Strong skills in constructing comprehensive evaluation frameworks that rigorously measure agent accuracy, safety, and latency beyond ad hoc testing.
• Experience collaborating directly with enterprise clients and leading technical discussions to transform vague business requirements into detailed technical specifications.
• Capability to own end-to-end use case implementation independently.
• Ability to perform well in dynamic, fast-changing, and ambiguous environments.

Preferred Qualifications

• Experience defining architectural standards for AI and agentic frameworks across distributed teams.
• Willingness and ability to adapt to unfamiliar technical domains, such as frontend development, to meet project needs.
• Exposure to regulated or sensitive sectors like finance, healthcare, or telecommunications.
• Understanding of enterprise-level security, compliance, and auditability requirements for AI technologies.