Location: Remote (Global) Compensation: Competitive, dependent on experience Type: Full-Time Contractor (2+ months, potential to extend) Reports to: Managing Partner About HELO Solutions HELO Solutions is an AI consulting and product development company. We build production AI systems — agents, automation platforms, and intelligent workflows — for enterprise clients across industries including CPG, financial services, legal, and music. We also develop our own AI products. We are a small, high-output team that ships fast, operates with minimal bureaucracy, and holds a high bar for work that actually runs in production and gets used. About the Role We are hiring an AI Engineer who has built agents that are live in production at real companies — not demos, not prototypes that died after a pitch, not research projects. We need someone who has shipped agentic systems that enterprises depend on every day, and who understands the full lifecycle: scoping the business problem, designing the agent architecture, integrating with messy enterprise systems, building evaluation and monitoring, and keeping it running reliably. This role sits across two priorities equally: building our internal multi-agent AI platform and delivering agent-based solutions directly to enterprise clients. You will work closely with our engineering team and the Managing Partner. You will have significant autonomy and direct impact on both the product and the business. Responsibilities • Design, build, and deploy AI agents and multi-agent systems that solve real business problems for enterprise clients. • Architect and implement agent orchestration — coordination, handoffs, shared state, and communication between specialized agents within our multi-agent platform. • Integrate agents with enterprise systems (ERPs, CRMs, accounting platforms, APIs) to execute workflows end-to-end in production environments. • Build evaluation frameworks and production monitoring for deployed agents — logging agent decisions, tracking accuracy, cost, and latency, and implementing feedback loops. • Work within client systems to understand existing workflows and translate messy business processes into agent-executable architectures. • Identify and codify repeatable deployment patterns across engagements to accelerate future delivery. • Maintain deep, current knowledge of LLM capabilities, agent frameworks, implementation patterns, and the evolving AI product development stack. • Deliver technical artifacts including agent skills, sub-agents, API integrations, and supporting infrastructure that will be used in production workflows. • Contribute to internal product development, shaping the architecture and capabilities of our platform alongside the engineering team. Requirements • Production agent experience — You have built AI agents that are currently running in production for real companies. You can point to systems you built that people use every day. • Python proficiency — Strong programming skills with Python as your primary language. You ship clean, maintainable production code. • LLM fluency — Deep working knowledge of prompt engineering, context window management, and model selection. You know when to use a smaller model vs. a frontier model and why. • Enterprise integration experience — You have connected agents to real business systems: ERPs (Acumatica, NetSuite, SAP), CRMs (Salesforce, HubSpot), accounting platforms (QuickBooks, Xero), or comparable enterprise APIs. • Evaluation and monitoring in production — You have built observability into agents. You know how to log agent decisions, track accuracy and cost, and build feedback loops that improve agent performance over time. • Multi-agent orchestration — You have designed or built systems where multiple specialized agents coordinate, hand off tasks, and share state to accomplish complex workflows. • High agency — You can take a messy business problem and turn it into a working agent architecture without hand-holding. You thrive in ambiguity and move fast with minimal direction. • Portfolio / case study — You must be able to walk us through at least one agent system you built that is live and being used by a real company. We want to understand the business problem, your architecture decisions, and how it is performing. Nice-to-Haves • TypeScript, Java, or a strong second language beyond Python. • Customer-facing or consulting experience — you have worked directly with clients or stakeholders to scope and deliver technical projects. • Domain experience in financial services, CPG, legal, or the music industry. • Cost optimization thinking — token management, caching strategies, model routing to keep agent operating costs viable for clients. • Experience with workflow orchestration tools (Temporal, Airflow, Step Functions, or similar). • Former technical founder or early-stage startup experience — you have worn many hats and shipped under resource constraints. How to Apply Send us your resume and a brief write-up of an agent system you built that is live in production. We want to know: What was the business problem? What was your architecture? How is it performing? If multiple people contributed, tell us which part was yours. Keep it concise — a few paragraphs is plenty. What We Offer • Remote-first, global team — work from anywhere. • Direct impact — you will shape both our products and our client engagements from day one. • Small team, no bureaucracy — decisions happen fast, your work ships fast. • Exposure to diverse enterprise AI challenges across multiple industries and verticals. • Competitive compensation dependent on experience. HELO Solutions LLC is a Delaware-based company. We are an equal opportunity employer committed to building a diverse team. Pay: $105,000.00 - $140,000.00 per year Application Question(s): • Name one AI agent you built that is currently running in production at a real company. What does it do? • You need to deploy 3 agents that each call different enterprise APIs. One API is flaky and times out 20% of the time. How do you handle this in production? • When would you use Claude Haiku instead of GPT-4o for an agent task, and why? Work Location: Remote