AI Engineer: Scale LLM-Driven Document Pipelines

Fdetimes; San Francisco (CA); On-site; USD 140,000 - 210,000; Full time

Benefits offered by this job

Unlimited PTO

Free lunch

Reimbursed transportation

Health insurance

Wellness budget

Parental leave

Job summary

Reducto is seeking an in-person Backend/AI Engineer in San Francisco to own core API work for document parsing at scale. You will integrate cutting-edge LLMs, optimize pipelines, and help shape product direction by partnering with founders and customers.

The role requires hands-on development across the full lifecycle, strong Python skills, and a bias for fast shipping with high quality. You’ll build internal tools and tooling to accelerate learning and iteration.

Qualifications

• 2+ years of experience building real world applications and integrating LLMs into production systems.
• Exceptional at Python.
• Experience building internal tools, e.g., Streamlit apps, to test hypotheses or create datasets.

Responsibilities

• Integrating and optimizing LLM calls for structured extraction, form filling, and document understanding tasks
• Making improvements to API design and pre-processing algorithms based on customer feedback
• Building and improving document processing pipelines that handle PDFs to spreadsheets at scale
• Experimenting with new techniques and output structures to improve LLM accuracy and reduce latency
• Building internal tooling and evals to better understand/analyze failure cases
• Working directly with the founders and customers to shape the product direction and engineering strategy

Skills

Python

LLM integration

Streamlit

Tools

LLM APIs

Streamlit

Job description

Reducto is seeking an in-person Backend/AI Engineer in San Francisco to own core API work for document parsing at scale. You will integrate cutting-edge LLMs, optimize pipelines, and help shape product direction by partnering with founders and customers.

The role requires hands-on development across the full lifecycle, strong Python skills, and a bias for fast shipping with high quality. You’ll build internal tools and tooling to accelerate learning and iteration.