Senior AI Engineer

GoTalent; United States; On-site; USD 170,000 - 210,000; Full time

Job summary

GoTalent is seeking a Senior AI Agent Engineer to design, build, and scale production-grade AI agent systems. You will own the end-to-end AI agent stack, including orchestration, tool-calling, memory management, retrieval systems, and guardrails.

The role requires hands-on work with LLMs, RAG, and multi-step reasoning in a fast-paced startup environment. The ideal candidate ships AI agent products for real customers, collaborates with product and engineering, and drives reliability and

Qualifications

• 5+ years of software engineering experience with a strong focus on AI and machine learning applications.
• Demonstrated experience shipping a complete AI agent system to real users in a production environment.
• Proven ownership of the full AI agent stack, including orchestration, tool-calling, memory management, retrieval systems, evaluation frameworks, guardrails and safety controls, etc.

Responsibilities

• Design, develop, and deploy production-scale AI agent systems that solve complex business problems.
• Own the end-to-end AI agent architecture, including agent orchestration, tool calling and function calling, memory systems, evaluation frameworks, safety, guardrails, and governance.
• Build and optimize Retrieval-Augmented Generation (RAG) systems using vector databases and modern retrieval techniques.
• Develop scalable workflows that enable agents to reason across structured and unstructured data.
• Create robust prompt engineering strategies and structured output frameworks to improve reliability and accuracy.
• Implement multi-step agent workflows with autonomous decision-making capabilities.
• Design, maintain, and optimize integrations between LLMs, external tools, APIs, and data sources.
• Establish evaluation methodologies, benchmarking processes, and monitoring systems to measure agent performance.
• Collaborate closely with product, engineering, and business stakeholders to translate requirements into production-ready AI solutions.
• Stay current with emerging AI frameworks, models, and agent architectures, applying best practices across the organization.

Skills

TypeScript

Mastra

AI agents

Prompt engineering

Function calling

Tool-calling systems

LLM orchestration

RAG

Vector databases

APIs integration

Tools

Mastra framework

Job description

Our client is seeking a highly experienced Senior AI Agent Engineer to design, build, and scale production-grade AI agent systems. This role requires a hands-on engineer with deep expertise in large language models (LLMs), agent orchestration, retrieval systems, and tool-calling frameworks. The ideal candidate has successfully shipped AI agent products to real customers and has owned the complete agent lifecycle, from orchestration and memory management to retrieval, evaluation, guardrails, and production monitoring.

This position is best suited for someone who thrives in fast-paced startup environments, can operate with minimal structure, and has a proven track record of delivering reliable, accuracy-critical AI systems at scale.

Key Responsibilities

• Design, develop, and deploy production-scale AI agent systems that solve complex business problems.
• Own the end-to-end AI agent architecture, including:
• Agent orchestration
• Tool calling and function calling
• Memory systems
• Evaluation frameworks
• Safety, guardrails, and governance
• Build and optimize Retrieval-Augmented Generation (RAG) systems using vector databases and modern retrieval techniques.
• Develop scalable workflows that enable agents to reason across structured and unstructured data.
• Create robust prompt engineering strategies and structured output frameworks to improve reliability and accuracy.
• Implement multi-step agent workflows with autonomous decision-making capabilities.
• Design, maintain, and optimize integrations between LLMs, external tools, APIs, and data sources.
• Establish evaluation methodologies, benchmarking processes, and monitoring systems to measure agent performance.
• Collaborate closely with product, engineering, and business stakeholders to translate requirements into production-ready AI solutions.
• Stay current with emerging AI frameworks, models, and agent architectures, applying best practices across the organization.

Required Qualifications

Experience

• 5+ years of software engineering experience with a strong focus on AI and machine learning applications.
• Demonstrated experience shipping a complete AI agent system to real users in a production environment.
• Proven ownership of the full AI agent stack, including:
• Orchestration
• Tool-calling
• Memory management
• Retrieval systems
• Evaluation frameworks
• Guardrails and safety controls
• Experience building accuracy-critical AI applications where reliability and consistency are essential.
• Hands-on experience designing systems that perform multi-step reasoning and workflow execution.
• Experience operating in startup environments with limited process and high levels of autonomy.

Technical Skills

• Strong proficiency in TypeScript.
• Experience with Mastra or comparable AI agent frameworks.
• Deep understanding of:
• AI Agents
• Prompt Engineering
• Function Calling
• Tool-Calling Systems
• LLM Orchestration
• Structured Outputs
• Retrieval-Augmented Generation (RAG)
• Vector Databases
• Experience integrating AI systems with APIs, databases, and third-party services.
• Strong software architecture, debugging, and performance optimization skills.

Preferred Qualifications

• Experience as a founding engineer or member of an early-stage startup team (first 10-20 employees or engineers).
• Previous startup founder or technical co-founder experience.
• Experience building AI systems that reason over structured data and complex business workflows.
• Experience with advanced memory architectures and long-term agent state management.Knowledge of AI evaluation methodologies, observability, and production monitoring.
• Contributions to open-source AI projects, frameworks, or developer tooling.

What Success Looks Like

• Deliver production-grade AI agent systems that provide measurable value to customers.
• Build reliable, secure, and scalable agent architectures capable of handling real-world complexity.
• Improve agent accuracy, latency, and performance through systematic evaluation and optimization.
• Establish best practices for AI orchestration, retrieval, memory, and tool usage across the organization.
• Drive innovation while maintaining engineering excellence and operational reliability.