Premier Global Links LLC is seeking an experienced Staff Applied AI Engineer to build and scale reliable AI capabilities for a growing health coaching platform. This role is ideal for a hands-on engineer who has shipped LLM-powered applications to production and enjoys owning the full AI development lifecycle from prototyping and evaluation through deployment, monitoring, and iteration.
The ideal candidate will have 4–10 years of applied AI engineering experience, Staff-level experience, strong Python skills, production experience with LLMs and AI agents, and a highly collaborative, curious, and results-driven mindset.
Key Responsibilities
- Build and ship production AI agents using LLMs, tool calling, structured outputs, and streaming responses.
- Develop AI-powered features supporting personalized guidance across sleep, nutrition, fitness, and wellness.
- Own the full AI development lifecycle, from prototyping and evaluation to deployment, monitoring, and continuous improvement.
- Develop and evaluate AI systems using frameworks such as LangChain and LangGraph.
- Improve AI reliability, latency, cost, and observability through prompt caching, token budgets, retry logic, and monitoring.
- Build production tools and API integrations using Pydantic validation, data search, and structured submissions.
- Design evaluation processes to measure AI safety, effectiveness, reliability, and personalization.
- Build and deploy production Python services and scalable AI infrastructure.
- Work closely with product, design, mobile, and backend engineers in a cross-functional environment.
- Apply direct feedback and data-driven insights to continuously improve AI features and systems.
Required Qualifications
- 4–10 years of experience in applied AI engineering or a closely related engineering role.
- Experience working at the Staff Engineer level or above.
- Hands-on experience deploying LLMs in production, including prompt engineering, tool calling, structured output, and evaluation.
- Strong experience building and deploying production Python services.
- Experience with AI agent frameworks such as LangChain or LangGraph.
- Experience with async Python, HTTP APIs, and streaming protocols such as SSE and webhooks.
- Strong software engineering and system design fundamentals.
- Ability to work independently and take ownership in a fast-changing environment.
- Comfortable giving and receiving direct feedback.
- Ability to work remotely within the continental United States and U.S. time zones.
Preferred Qualifications
- Experience transitioning from a large technology organization into a startup environment.
- Experience as a co-founder or founding engineer.
- Previous experience at large technology companies such as Amazon or Meta.
- Experience working with AI products in healthcare, fitness, wellness, or related fields.
- Experience with AI evaluation, observability, and production monitoring.
- Background with Y Combinator or other high-growth startup environments.
- Location in San Francisco, CA.
Work Schedule
Remote: Full-time remote position within the continental United States.
The role operates in a fast-paced, highly collaborative environment with close partnership across engineering, product, design, mobile, and backend teams.
Compensation
$250,000–$300,000 per year + equity opportunities.
Additional compensation flexibility may be available for exceptional candidates, including potential sign-on bonuses.
Benefits
- Competitive equity opportunities.
- Learning and development support.
- Wellness stipend.
- Competitive company benefits.
- Opportunity to build production AI systems and shape the foundation of a growing health coaching platform.
LLC is an Equal Opportunity Employer. Qualified applicants will be considered without regard to race, color, religion, sex, national origin, age, disability, veteran status, or any other status protected by applicable law.
Originally posted on