AI Agent Engineer
ChaiONE
Salary undisclosed
Need a reasonable accommodation to apply or interview? Contact us.
JobMinglr uses automated technology to recommend jobs based on profile information and job preferences. Match Score does not determine eligibility for a position, prevent a user from viewing or applying to a job, or make hiring decisions on behalf of an employer.
Description
Lead AI Engineer (AI Agents, Automation & Multimodal Systems)
Location: Remote / Hybrid (if local)
Employment Type: Full-Time
Level: Senior / Lead IC
Reports To: Head of AI / CTO / Engineering Leadership
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.
About this role
ChaiONE is looking for a Lead AI Engineer to own the full lifecycle of AI agent systems—from architecture and development through production deployment. You'd work across language models, voice, vision, and automation, designing systems that combine LLMs, APIs, and orchestration frameworks to solve real business problems. This is a hands-on role where you'll both build systems yourself and set technical direction for the team, making decisions about when to use AI versus deterministic approaches and defining standards for reliability and safety.
The work spans multiple domains: designing scalable multi-agent architectures, developing prompt strategies across different models, building end-to-end workflows using tools like LangGraph and n8n, leading production voice agent design, and integrating vision models into agent decision-making. You'll also own evaluation frameworks, monitoring, and continuous improvement in production, while mentoring junior engineers and collaborating with product and design teams to translate business needs into AI solutions.
This role suits someone with 6+ years of software engineering experience and deep hands-on work with production AI systems—not prototypes. You'll need strong Python or TypeScript skills, solid backend and API integration experience, and a track record building reliable, scalable systems. Voice agent experience, familiarity with agent frameworks like LangGraph or AutoGen, and startup experience are valuable. The position is full-time, hybrid in Houston, and offers direct ownership of an emerging AI platform with meaningful impact on product direction.
This role's local market on JobMinglr
Pay for this role
The employer didn't post a pay range for this role. That usually means pay is set in negotiation, which favors whoever arrives with numbers. Check ranges on comparable AI Agent Engineer postings in Houston, and analyze any offer before you accept it.
Before you apply, worth reading
How JobMinglr reads this job
Every listing here is scored against your profile before you apply: skills overlap, experience level, location and work arrangement, each weighted and explained. You see the score and the reasons, not just a list. How the matching works.