Lead AI Engineer (Agentic Systems)

Location: Remote-first with overlap during US Eastern hours; requires monthly travel on average to a single US major metro and periodic on-site client embedding.

Company

hirify.global is an AI transformation firm that builds production AI systems for mid-market enterprises in regulated and technical domains.

What you will do

• Lead the architecture and development of a multi-agent orchestration platform with capability agents for data ingestion, requirements retrieval, model construction, simulation orchestration, QA, and report generation.
• Define interface contracts and integrations with domain-specific simulation tools and client software teams.
• Design and build the orchestration engine, including state management, error recovery, audit trails, monitoring dashboards, and agent design patterns.
• Extend an existing production RAG system with established retrieval infrastructure and interaction telemetry.
• Run pilot iterations with senior client engineers, measure time savings, capture failure modes, and improve system reliability.
• Mentor a junior builder and contribute to technical hiring.

Requirements

• 6+ years of production software engineering experience, including 2+ years shipping LLM-based or agentic systems in production.
• Strong Python skills and hands-on experience with an agent framework such as LangGraph, Letta, or custom orchestration.
• Experience with RAG architectures, vector databases, embedding models, document-processing pipelines, and retrieval evaluations.
• Strong understanding of LLM evaluations, agent reliability, debugging, and failure-mode analysis.
• Ability to communicate clearly with engineers, executives, non-engineers, and domain experts in client-facing settings.
• Willingness to overlap with US Eastern time and travel monthly on average to a US major metro for periodic on-site client work.

Nice to have

• Forward-deployed or solutions-engineering experience at an AI lab, applied AI firm, or similar organization.
• Experience integrating LLMs with deterministic engineering tools, simulators, or specialized APIs.
• Cloud infrastructure experience with AWS, Azure, or GCP.
• Exposure to regulated or technical domains such as financial services, healthcare, legal, or industrial sectors.

Culture & Benefits

• Remote-first working model with modern development and deployment tooling.
• Production use of Claude, OpenAI APIs, open-source models, Cursor, Claude Code, Vercel, Neon, and Sentry.
• Focus on shipping working systems rather than AI strategy presentations or proof-of-concept demos.
• Eight-month term with likely extension; available as a full-time or contract engagement.
• Technical lead seat reporting directly to the founder.

Hiring process

• Submit a short cover letter explaining background, shipped work, and interest in the role.
• Describe a multi-agent or production LLM system built, including what worked, what failed, and what would be changed.
• GitHub, code samples, or a CV are optional.