Remote AI/LLM Engineer

1w1 week ago

Ostro

US · Full-time · $159,300 – $202,400

About this role

At Ostro, we are transforming how life sciences connect with the people who need their innovations most using patent-pending AI technology. We seek an AI/LLM Engineer to scale and expand established AI/LLM products, focusing on next-generation features for our SaaS platform. This role emphasizes integrating large language models while balancing speed and maintainability.

Design and deliver scalable services with a strong emphasis on LLM integration. Collaborate with cross-functional teams to implement new features and refine AI/LLM capabilities. Support engineering best practices through reliable testing, clean architecture, and low technical debt at startup speed.

We are a remote-first team uniting experts from leading healthcare organizations and innovative tech companies. Ostronauts share curiosity, honesty, and passion for improving healthcare. Cultural values include Put People First, Win as a Team, Act with Urgency and Scrappiness, and Embrace Ambiguity Fearlessly.

Provide feedback on roadmap and features for AI/LLM initiatives. Stay informed on emerging technologies, prompt engineering, and trends. Join us to make measurable impact on global health and shape intelligent life sciences commercialization.

Requirements

Experience shipping LLM pipelines including preprocessing, prompt optimization, output validation, and fallback mechanisms
Experience with production use of LLM APIs (e.g., OpenAI, Gemini)
Experience building systems to measure model performance, detect drift, and ensure output quality
Proficiency in Django/Python for backend development
Experience with PostgreSQL for data management
Familiarity with GCP for cloud infrastructure
Knowledge of OpenAI, Vertex, and other public LLM APIs

Responsibilities

Develop performant, scalable, and high quality APIs and backend processes for Ostro's SaaS platform, with a strong emphasis on LLM integration
Collaborate with cross-functional teams to implement new features and refine existing ones, particularly those involving AI/LLM capabilities
Provide feedback on roadmap and features for your team, contributing to the strategic direction of Ostro’s AI/LLM initiatives
Ensure code quality and compliance through thorough reviews, unit testing, and adherence to best practices for LLM-powered applications
Optimize application performance and scalability to meet user demands, especially for LLM inference and data processing
Stay informed about emerging AI/LLM technologies, prompt engineering techniques, and industry trends
Troubleshoot and resolve production issues, ensuring performance, reliability, and scalability of LLM-driven features

Benefits

Remote-first team environment
Collaborative culture with experts from healthcare, life sciences, and top tech companies
Work on AI-powered omnichannel engagement trusted by majority of world’s top 20 pharmaceutical companies
Opportunity to build future of life sciences and improve global health