Company Overview

This YC-funded health-tech startup is revolutionizing the life sciences industry by automating the creation of critical R&D and regulatory documentation. By leveraging advanced LLM workflows, they enable biopharma companies—ranging from innovative startups to global pharmaceutical giants—to move from "months to minutes" in their FDA submission processes. Their mission is to accelerate the delivery of life-saving treatments to patients by removing the administrative bottlenecks of drug development.

What Makes It an Awesome Place to Work

High-Impact Mission: Directly contribute to getting life-saving medicines to patients faster by solving complex regulatory hurdles.
Top-Tier Pedigree: Connect and work directly with founders of a high-growth, YC-funded startup.
Cutting-Edge Tech Stack: Build with the latest frontier models (OpenAI, Anthropic, Google) and shape the future of AI agents in regulated industries.
In-Person Collaboration: Located in the vibrant Mission Bay hub of San Francisco, fostering high-intensity innovation and rapid iteration.
Unique Culture: A team that values deep technical R&D, rapid experimentation, and a quirky sense of humor (from Mongol postal history to matcha KitKats).

Scope of Role and Experience

As an Applied LLM Engineer, you will:

Develop, scale, and expand a platform that supports regulatory needs for global pharma companies.
Design multi-step LLM workflows, task-specific agents, and advanced RAG pipelines.
Build and maintain production-grade backend systems and APIs from the ground up using Python (FastAPI/Django).
Conduct technical R&D to explore the boundaries of model functionality and translate findings into production features.
Orchestrate and evaluate LLM-driven systems, identifying issues across model outputs and system logic.

You have:

3+ years of software development experience with a focus on building and deploying AI/ML applications.
Proven expertise in backend engineering (Python, FastAPI, Django) and cloud infrastructure (AWS/GCP/Azure).