Senior AI Pipeline Engineer (Python / AWS / LLMs)

About Inhubber

Inhubber is a security-first Contract Lifecycle Management (CLM) platform designed for organizations with high compliance and data protection requirements. Our platform combines:

• End-to-end encryption
• Cloud infrastructure
• AI document intelligence to make complex contracts understandable and manageable.

We are building a security-first AI platform for contract intelligence. Our system processes sensitive legal documents for companies worldwide, combining:

• End-to-end encryption
• Modern cloud infrastructure
• Advanced AI document analysis

We are now scaling our AI document pipelines and GenAI capabilities.

About the Role

We’re looking for a Senior AI Pipeline Engineer who wants to own real production AI systems, not just experiments.

What You Will Own

You will take ownership of our AI document processing pipelines. Your work will power:

• Automated contract analysis
• Structured data extraction
• Legal document Q&A
• Next-generation AI contract drafting

This is a hands-on engineering role, not research. You will build reliable AI pipelines that run in production at scale.

What You'll Work On

• Production AI pipelines: Maintain and improve our Python document processing pipelines running on AWS Lambda + S3 + Docker.
• LLM-powered extraction: Improve contract interpretation and structured extraction using LLMs, structured outputs, and retrieval pipelines.
• New document pipelines: Design and ship new pipelines for additional document types with evaluation datasets and regression checks.
• GenAI systems: Help build the foundations for agentic contract drafting and interpretation systems.
• Reliability & operations: Improve observability, monitoring, cost control, and failure handling for real production workloads.

Our Tech Stack

• Python
• AWS Lambda
• Docker
• S3
• Azure
• LLM APIs
• React / TypeScript
• Java backend

Requirements

• Strong production Python experience
• Experience owning real production systems
• AWS serverless experience (Lambda + S3)
• Docker / containerized services
• Experience with LLM pipelines

Ideally Also

• RAG pipelines
• Structured outputs
• Evaluation / test datasets
• Document AI (OCR / PDFs)

Why This Role Is Interesting

You will be working on one of the hardest real-world AI problems: Turning unstructured legal documents into reliable structured intelligence. This requires solving challenges in:

• Document parsing
• LLM reliability
• Evaluation systems
• Pipeline orchestration
• AI safety and validation