Prompt Engineer

Archon Agents — United States · Posted ~7 hours ago

Full-time

Skills

AI engineering Agentic workflows Software engineering Applied machine learning API development System integrations Containerization Model deployment Evaluation Monitoring Alerting AI models APIs Containers Machine learning

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

An AI engineering role focused on turning models and agent workflows into reliable production systems operating on real client data. Responsibilities include building agentic workflows, tools, APIs and integrations; connecting business systems; packaging services in reproducible containers; and implementing evaluations, monitoring, and alerts for accuracy, drift, and reliability.

Highlights

Hands-on opportunity to operationalize AI in production, spanning agentic workflows, integrations, model and service deployment, evaluation, monitoring, and reliability. The role offers broad ownership across architecture through governed deployment.

Description

Archon Agents is a managed AI operations company led by Managing Partner Michael DeLucca and built by the team at BMI Studios. We design, deploy, and run governed AI workforces that produce real production work for agencies, operators, and enterprise teams. We are a senior team headquartered in Las Vegas, and we measure success by what ships, not by demos. As an AI Engineer at Archon, you will operationalize AI by turning models and agent workflows into reliable production systems that run against real client data. You sit between software engineering and applied machine learning, owning the path from architecture to a governed, monitored deployment. What you will do Design, build, and deploy agentic workflows, tools, APIs, and integrations.Connect client systems such as CRMs, data warehouses, messaging, and internal APIs.Package and ship models and services in containerized, reproducible environments.Implement evals, monitoring, and alerting for accuracy, drift, and reliability. What we are looking for 2+ years building and deploying software, ML, or AI systems in production.Strong Python plus LLM tooling such as LangChain, RAG, and vector databases.Familiarity with a major cloud (AWS, GCP, or Azure), Docker, and API design.Clear communication and a strong bias toward shipping. Full-time salaried position with full benefits. Starting at $120,000, based on experience. Apply for this role →