AI Agent Engineer

Lead AI Engineer

Location: Remote / Hybrid (if local) Employment Type: Full-Time Level: Senior / Lead IC

About the Role:

We're seeking a Lead AI Engineer to own the architecture, development, and deployment of next-generation AI agent systems across language, voice, vision, and automation. This role is ideal for someone who thrives at the intersection of engineering rigor and applied AI, and who can turn emerging AI capabilities into reliable, production-grade systems. You'll lead the design of AI-powered workflows that combine LLMs, APIs, multimodal models, automation platforms, and conversational interfaces to solve real business problems. This role is both hands-on and strategic—you'll build systems yourself while setting technical direction, standards, and best practices for the team.

What You'll Do:

AI Architecture & Agent Systems:

• Design and implement scalable AI agent architectures using LLMs, tool calling, retrieval, memory, and orchestration frameworks.
• Own multi-step, multi-agent workflows for complex tasks and decision-making.
• Make architectural decisions around when to use LLMs vs. deterministic systems.

Prompt Engineering & Model Strategy:

• Lead prompt strategy across models (GPT-4, Claude, Gemini, open-source models).
• Develop reusable prompt patterns, chains, and templates.
• Ensure prompts are optimized for reliability, safety, latency, and cost.

Workflow Automation & Integrations:

• Architect and build end-to-end AI workflows using tools like n8n, LangGraph, AutoGen, or custom orchestration layers.
• Integrate AI agents with backend systems (CRMs, databases, internal tools, third-party APIs).
• Implement robust error handling, retries, observability, and logging.

Conversational AI & Voice Systems:

• Lead design of production-grade voice agents and conversational systems.
• Define best practices for spoken dialogue, intent handling, fallback strategies, and escalation paths.
• Ensure compliance, safety, and reliability in voice and conversational use cases.
• Optimize for low latency, natural language flow, and user trust.

Vision AI & Multimodal Systems:

• Design and deploy multimodal workflows combining vision, language, and automation.
• Apply vision models for use cases such as object detection, quality control, or document understanding.
• Integrate vision outputs into downstream agent decision-making.

Testing, Evaluation & Reliability:

• Define evaluation frameworks for AI outputs (accuracy, hallucination risk, safety, bias).
• Build automated testing and QA pipelines for agent systems.
• Monitor performance in production and continuously improve systems.

Leadership & Mentorship:

• Set technical standards and best practices for AI development.
• Mentor interns and junior engineers on AI workflows and engineering rigor.
• Collaborate closely with Product, Design, and Enablement teams to translate business needs into AI solutions.

Requirements:

What We're Looking For:

Required:

• 6+ years of experience in software engineering, with deep focus on applied AI systems.
• Strong experience working with LLMs and AI APIs (OpenAI, Anthropic, Google, or similar).
• Proven experience building production AI systems, not just prototypes.
• Strong programming skills in Python and/or JavaScript/TypeScript.
• Experience with APIs, microservices, and backend integrations.
• Strong understanding of system reliability, scalability, and observability.
• Excellent communication skills and ability to explain complex systems clearly.

Preferred / Bonus:

• Experience with agent frameworks (LangChain, LangGraph, AutoGen, CrewAI).
• Experience building voice agents or conversational AI systems.
• Experience with computer vision or multi modal models.
• Familiarity with no-code/low-code automation tools (n8n, Zapier).
• Experience working in small, fast-moving teams or startups.

Benefits:

What You'll Gain:

Ownership of cutting-edge AI systems from concept to production. Opportunity to define and scale an AI agent platform. Direct impact on product direction and business outcomes. Leadership growth through mentoring and technical decision-making. Competitive compensation and growth opportunities (details shared during process).

Why This Role Matters:

This role is not about experimentation alone—it's about turning AI into dependable infrastructure. You'll help shape how AI is responsibly and effectively used across the organization, setting the foundation for future innovation.