AI Engineer

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

Job summary

Goliath Partners is seeking an engineer to own AI infrastructure powering autonomous systems and LLM-driven workflows, turning cutting-edge research into scalable production products.

You will prototype prompting, model coordination, and testing while shaping architecture and best practices for a rapidly growing AI organization.

Qualifications

• Bachelor’s, Master’s, or PhD in CS, EE, or related field.
• Experience developing AI-powered software and LLM apps.
• Knowledge of LLM-based systems: agent design, tool calling, retrieval, prompting, orchestration.
• Proven ability turning research concepts into production systems.
• Thrives in a fast-moving, evolving tech environment.
• Base Salary: $220,000–$275,000 depending on experience.

Responsibilities

• Lead development of infrastructure powering autonomous AI systems.
• Engineer AI-driven workflows capable of reasoning through tasks and taking actions.
• Build model-selection and coordination systems for different tasks.
• Create extensible architecture supporting multiple LLM providers.
• Develop monitoring systems for AI behavior and performance.
• Create testing methodologies and benchmarks for complex workflows.
• Translate AI research ideas into dependable, customer-facing engineering solutions.
• Prototype prompting, retrieval, fine-tuning, model selection, and agent strategies.
• Contribute to architectural decisions and engineering best practices.

Skills

AI infrastructure

LLM systems

Agent design

Model orchestration

Software engineering

Testing & benchmarking

Education

Bachelor’s/Master’s/PhD in CS/EE

Tools

Tool calling

Retrieval

Prompting

Model selection

Agent coordination

Job description

We’re partnering with an innovative AI company developing next-generation software that can reason through and automate sophisticated business processes. The team is building production-grade AI infrastructure that combines large language models, autonomous agents, and intelligent decision-making to tackle workflows that traditionally require significant human involvement.

This role is ideal for an engineer who enjoys working across AI infrastructure, autonomous systems, LLMs, and applied machine learning and wants to turn rapidly evolving AI capabilities into scalable products. You’ll have significant ownership over the systems that power intelligent automation, from agent execution and model coordination to testing, evaluation, and continuous improvement

What You’ll Work On

• Lead development of the infrastructure powering autonomous AI systems, including agent execution, tool integration, memory, state, and interaction with external applications.
• Engineer AI-driven workflows capable of reasoning through complex tasks, taking actions, maintaining context, and adapting based on outcomes.
• Build model-selection and coordination systems that dynamically determine which models, tools, or strategies should be used for different tasks.
• Create an extensible architecture capable of supporting multiple LLM providers and adapting as new models and capabilities emerge.
• Develop evaluation and monitoring systems that provide visibility into AI behavior, system quality, and performance over time.
• Create testing methodologies and benchmarks for complex, non-deterministic workflows that cannot be adequately measured through traditional software testing.
• Take ideas and techniques emerging from AI research and transform them into dependable, customer-facing engineering solutions.
• Rapidly prototype and iterate on prompting, retrieval, fine-tuning, model selection, and agent strategies to improve reliability and performance.
• Contribute to architectural decisions, engineering best practices, and the continued growth of the AI engineering team.

What You Bring

• Strong foundation in computer science, with a Bachelor’s, Master’s, or PhD in Computer Science, Electrical Engineering, or a related technical discipline preferred.
• Professional experience developing and deploying AI-powered software, LLM applications, autonomous agents, or intelligent automation products.
• Strong knowledge of LLM-based systems, including agent design, tool calling, retrieval, prompting, model selection, and orchestration.
• Experience taking experimental or research-driven AI concepts and converting them into stable, scalable production systems.
• Ability to work effectively in a fast-moving environment where the underlying technology and best practices are evolving rapidly.
• Base Salary: $220,000 - $275,000, depending on experience
• High level of ownership and the opportunity to directly influence the architecture and direction of a rapidly scaling AI organization