AI Agent Engineer (Agent Orchestration & Full Stack Development)

Role Overview

The Agent Orchestrator will act as an Agent Boss and Forward-Deployed Engineer, responsible for designing, governing, and operating AI agent ecosystems. This role heavily leverages Anthropic plugins and advanced LLM integrations to automate complex business workflows while maintaining the highest standards of security, governance, and responsible AI.

Key Responsibilities

Agent Orchestration & Supervision

- Design, build, and manage multi-agent workflows across business functions.

- Leverage Anthropic plugins and automation frameworks to create task-specific agents.

- Define agent responsibilities, sequencing, escalation paths, and fallback mechanisms.

Model Evaluation & Performance

- Continuously evaluate agent outputs for accuracy, relevance, safety, and reliability.

- Implement monitoring, logging, and performance metrics to detect drift and failures.

- Establish human-in-the-loop feedback mechanisms to improve agent quality.

Governance, Security & Responsible AI

- Enforce strong AI governance, guardrails, and policy controls.

- Implement role-based access, audit trails, and approval workflows.

- Ensure compliance with data privacy, security, and responsible AI standards.

Forward-Deployed Engineering

- Work closely with customers and internal teams to deploy agents into real workflows.

- Integrate agents with enterprise systems such as CRMs, ERPs, and internal platforms.

- Translate business requirements into scalable agent designs.

Automation Strategy & Scaling

- Define strategies to scale agent orchestration across teams and domains.

- Balance automation with human oversight to ensure trust and reliability.

Qualifications

Experience

• 2 - 6 years of experience in software engineering, automation, AI integration, or systems orchestration.
• Hands-on experience working with large language models and agent-based systems.

Technical Skills

• Proficiency in Python, TypeScript, or similar languages.
• Experience with APIs, workflow orchestration, and system integrations.
• Familiarity with Anthropic plugins or comparable LLM plugin ecosystems.

Governance & Mindset

• Strong understanding of security, compliance, and responsible AI principles.
• Experience implementing safeguards such as access controls, logging, and rollback mechanisms.

Soft Skills

• Strong problem-solving and analytical skills.
• Excellent communication and cross-functional collaboration abilities.
• High ownership mindset with attention to quality and trust.

Additional Platform & Tool Proficiency

• Hands-on proficiency with modern AI development and orchestration platforms including Claude (Anthropic), Gemini (Google), Codex, and GHCP (GitHub Copilot Platform).
• Ability to evaluate, compare, and select the right models and tools based on use-case, performance, cost, security, and compliance considerations.
• Experience orchestrating workflows across multiple LLM providers while maintaining consistent governance, observability, and security controls.
• Familiarity with prompt engineering, tool/function calling, and plugin-based extensibility across these platforms.