Own the implementation of end-to-end agentic AI workflows, from data ingestion and schema design to prompting, context management, tool creation, and multi-agent orchestration
Partner closely with medicinal chemists to prototype, test, and refine AI-assisted workflows that improve scientific quality, speed, and confidence
Improve real user use cases by incorporating feedback from internal users (and external customers post-launch), translating insights into product and system improvements
Support automated integration of customer assay and experimental data into Indy environments, ensuring reliability and scalability
Identify and implement product improvements or new features based on hands-on collaboration with scientific, product, and engineering stakeholders
Contribute to backend and system architecture decisions as the platform evolves from single-user workflows to scalable, multi-user production systems

Requirements

4+ years of experience building backend and/or data systems using Python in production environments
Experience shipping at least one user-facing system that integrates LLMs (agentic workflows are a strong plus)
Strong understanding of backend systems, data flows, and production infrastructure
Comfort working with data engineering concepts such as schema design, pipelines, and orchestration (Dagster, Airflow, or similar tools)
Ability to collaborate deeply and effectively across disciplines, including working directly with scientists and translating domain-specific needs into robust technical solutions
Comfortable owning ambiguous problems, building from first principles, and iterating quickly in a startup environment

Benefits

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Pythonbackend systemsdata systemsdata ingestionschema designdata pipelinesmulti-agent orchestrationLLMssystem architectureproduct improvements

collaborationproblem-solvingiterationcommunicationtranslating domain-specific needs