AI Engineer

Goliath-Partners; San Francisco (CA); Hybrid; USD 220,000 - 275,000; Full time

Benefits offered by this job

Ownership potential

Hybrid work model

Career growth in AI

Job summary

Goliath-Partners in San Francisco seeks an AI engineer to lead infrastructure for AI agents, including tool execution, state, memory, and workflow coordination. You will build scalable agent systems, design model orchestration, and enable multi-provider support for rapid foundation-model changes.

You will prototype prompting, retrieval, fine-tuning, model selection, and agent design, influencing the technical roadmap and contributing to a high-performing AI engineering team in a hybrid work

Qualifications

• Bachelor's, Master's, or PhD in CS, EE, or related technical discipline from a strong academic institution.
• Proven experience developing and deploying LLM-based products, autonomous agents, or AI-driven automation systems.
• Strong knowledge of agent architectures, LLM APIs, tool calling, retrieval systems, prompting techniques, model selection, and orchestration.
• Experience turning experimental or research concepts into robust, production-quality systems.
• Strong software engineering skills and ability to work in a fast-moving, technically ambitious environment.
• Comfortable experimenting quickly, measuring results, and iterating based on empirical performance.

Responsibilities

• Architect and maintain the infrastructure powering AI agents, including tool execution, computer interaction, state, memory, and workflow coordination.
• Build agent systems capable of reasoning through and executing complex, multi-stage business processes.
• Develop model orchestration and routing systems that dynamically determine the best model or strategy for a given task.
• Create an adaptable AI infrastructure layer that can support multiple model providers and rapidly changing foundation-model capabilities.
• Design evaluation pipelines that continuously measure agent quality, reliability, and performance while catching regressions before deployment.
• Establish benchmarks and testing methodologies for complex, open-ended agent workflows that cannot be evaluated effectively through conventional methods.
• Convert advances in LLMs, agent frameworks, tool use, and computer-use technology into scalable production capabilities.
• Rapidly prototype and iterate across prompting, retrieval, fine-tuning, model selection, and agent design to improve outcomes.
• Influence architecture, engineering practices, and the broader technical roadmap as the organization scales.
• Contribute to building and expanding a high-performing AI engineering team.

Skills

LLM APIs

Agent architectures

Tool calling

Retrieval systems

Prompting techniques

Model orchestration

Production-grade systems

Software engineering

Education

Bachelor's/Master's/PhD in CS/EE

Job description

We’re partnering with a rapidly scaling AI company developing intelligent systems that automate sophisticated, high-impact workflows for enterprise organizations. This role sits at the core of the company’s AI engineering efforts, with a focus on agent infrastructure, LLM systems, model orchestration, evaluation, and production-grade AI applications.

You’ll operate across applied AI research and software engineering, taking new advances in foundation models and agent technology and transforming them into dependable products that solve real-world customer problems.

What You’ll Do

• Architect and maintain the infrastructure powering AI agents, including tool execution, computer interaction, state, memory, and workflow coordination.
• Build agent systems capable of reasoning through and executing complex, multi-stage business processes.
• Develop model orchestration and routing systems that dynamically determine the best model or strategy for a given task.
• Create an adaptable AI infrastructure layer that can support multiple model providers and rapidly changing foundation-model capabilities.
• Design evaluation pipelines that continuously measure agent quality, reliability, and performance while catching regressions before deployment.
• Establish benchmarks and testing methodologies for complex, open-ended agent workflows that cannot be evaluated effectively through conventional methods.
• Convert advances in LLMs, agent frameworks, tool use, and computer-use technology into scalable production capabilities.
• Rapidly prototype and iterate across prompting, retrieval, fine-tuning, model selection, and agent design to improve outcomes.
• Influence architecture, engineering practices, and the broader technical roadmap as the organization scales.
• Contribute to building and expanding a high-performing AI engineering team.

What We’re Looking For

• Strong foundations in computer science, with a Bachelor’s, Master’s, or PhD in Computer Science, Electrical Engineering, or a related technical discipline from a strong academic institution preferred.
• Proven experience developing and deploying LLM-based products, autonomous agents, or AI-driven automation systems.
• Strong knowledge of agent architectures, LLM APIs, tool calling, retrieval systems, prompting techniques, model selection, and orchestration.
• Experience taking experimental or research-oriented AI concepts and engineering them into robust, production-quality systems.
• Strong software engineering skills and the ability to work effectively in a fast-moving, technically ambitious environment.
• Comfortable experimenting quickly, measuring results, and iterating based on empirical performance.

Compensation & Benefits

• Base Salary:$220,000 – $275,000, depending on experience
• Location: San Francisco, CA, Hybrid
• Significant ownership, autonomy, and opportunity to influence the technical direction of a rapidly growing AI company