Frontier Agents Engineer (Forward Deployed Engineering)

About the job

Responsibilities

• Architect and deploy production AI systems integrating with enterprise environments like cloud platforms, data warehouses, and internal APIs.
• Design scalable agent architectures combining LLMs, retrieval, memory, tools, and enterprise data.
• Build integrations for AI agents to safely interact with customer systems, meeting security and compliance requirements.
• Rapidly prototype new AI capabilities and evolve them into production-ready systems.
• Build production infrastructure for reliable enterprise AI software, including agent runtimes and orchestration frameworks.
• Engineer systems for reliability, observability, latency, and scalability.
• Design human-in-the-loop workflows combining AI automation with expert oversight.
• Build deployment patterns for safe evolution of AI systems through continuous delivery.
• Operationalize AI quality systems to ensure production agents remain reliable.
• Deploy evaluation harnesses using various methods to detect quality regressions.
• Implement tracing, observability, monitoring, guardrails, and safety mechanisms for AI systems.
• Partner with Applied AI engineers to productionize new evaluation methodologies and AI capabilities.
• Rapidly evaluate new models, agent frameworks, and tooling for safe adoption into production.
• Partner with enterprise customers to understand their technical infrastructure and workflows.
• Translate ambiguous customer problems into scalable production AI architectures.
• Collaborate with customer teams to deploy AI into mission-critical workflows.
• Identify reusable engineering patterns for enterprise deployments.
• Serve as the primary technical advisor for strategic enterprise accounts.
• Lead architecture discussions on distributed systems, AI infrastructure, and enterprise integration.
• Document reusable architecture patterns, deployment strategies, and operational best practices.
• Work with product, infrastructure, and Applied AI teams to improve the platform.

Requirements

• Experience with modern software engineering, distributed systems, and cloud infrastructure.
• Familiarity with frontier AI technologies.
• Ability to design production agent architectures.
• Experience integrating with customer systems.
• Experience deploying AI into mission-critical workflows.
• Experience shaping engineering best practices for enterprise AI.
• Experience solving difficult systems problems.
• Experience rapidly prototyping new AI capabilities.
• Experience bringing frontier AI into production.
• Experience with LLMs, retrieval, memory, tools, and structured knowledge.
• Experience with enterprise requirements for security, governance, and compliance.
• Experience with agent runtimes, orchestration frameworks, context pipelines, and execution services.
• Experience with reliability, observability, latency, scalability, retries, fallback strategies, and graceful degradation.
• Experience with human-in-the-loop workflows.
• Experience with continuous delivery and experimentation for AI systems.
• Experience with AI quality systems, evaluation harnesses, offline benchmarks, online experiments, golden datasets, and regression suites.
• Experience with LLM-as-a-Judge for quality detection.
• Experience with tracing, observability, monitoring, guardrails, grounding, and safety mechanisms.
• Experience evaluating newly released models, agent frameworks, and developer tooling.
• Experience understanding customer technical infrastructure, software architecture, and operational workflows.
• Experience translating ambiguous customer problems into scalable production AI architectures.
• Experience collaborating with customer software engineers, ML engineers, platform teams, and product organizations.
• Experience identifying reusable engineering patterns.
• Experience serving as a primary technical advisor for enterprise accounts.
• Experience leading architecture discussions.
• Experience documenting architecture patterns, deployment strategies, and operational best practices.
• Experience working with product, infrastructure, and Applied AI teams.