AI Engineer — Agents & GenerAI

About the Role

Join the founding team to develop the core AI technologies that drive both client solutions and proprietary products. This position involves hands-on, comprehensive engineering tasks, ranging from creating initial prototypes to running pipelines in production environments, complete with evaluation metrics and safeguards to ensure performance integrity.

Key Responsibilities

• Develop applications utilizing large language models, including building retrieval systems, tool-using agents, orchestration mechanisms, and memory modules.
• Implement evaluation frameworks and observability tools to ensure quality is quantitatively assessed rather than assumed.
• Take full accountability for latency, cost efficiency, and system reliability within production environments.
• Collaborate across the technology stack to provide access to models through clean, well-documented APIs.

Candidate Profile

• Proficient in Python with strong foundational software engineering skills.
• Demonstrated experience deploying large language model applications such as agents or fine-tuned models to live users.
• Familiarity with cloud platforms, containerization, and continuous integration to successfully deploy developed solutions.
• A results-driven mindset with the ability to discern when features meet quality standards for release.

Preferred Qualifications

• Experience working with speech recognition or multimodal AI systems.
• Contribution to open-source projects or published research in relevant fields.