Engineering Knowledge Graph Engineer

BioArk Genome Engineering Operating System (BioArk GEOS) 

Project Vision 

• Current CRISPR software mainly focuses on guide RNA design or individual bioinformatics 

tasks, while successful genome engineering requires engineering strategy selection, feasibility 

analysis, laboratory planning, sequencing validation, quality control, and continuous 

optimization. 

• The BioArk AI CRISPR Engineering Platform is an AI Engineering System implementing a 

Design–Build–Test–Learn (DBTL) workflow. 

• Bioinformatics is treated as one component of a larger engineering ecosystem. 

• The platform leverages biomedical AI systems (e.g. Biomni) for biological reasoning while 

BioArk develops proprietary engineering intelligence, laboratory planning, sequencing 

interpretation and continuous learning.

Engineering Knowledge Graph & Continuous Learning Agent Engineers

Role Summary

You will build the AI Engineering Knowledge & Continuous Learning Engine, the intelligence core of the BioArk Genome Engineering Operating System that transforms every completed engineering project into reusable knowledge, continuously improving AI decision-making, Digital Twin prediction, laboratory planning, and engineering optimization.

Key Responsibilities

• Develop enterprise-scale Engineering Knowledge Graphs and AI knowledge bases that integrate biological knowledge, engineering data, laboratory experience, and historical project outcomes. 
• Build continuous learning systems that automatically convert experimental results into reusable engineering intelligence using machine learning, reinforcement learning, RAG, and AI knowledge retrieval. 
• Develop predictive models for engineering success, technical risk, Digital Twin optimization, and genome engineering parameter optimization based on historical project performance. 
• Design closed-loop learning systems that continuously improve engineering decision-making, laboratory planning, and AI prediction models across the entire Design–Build–Test–Learn (DBTL) workflow. 

Deliverables

Engineering Knowledge Graphs, Self-Learning Engineering Knowledge Bases, AI Prediction Models, Engineering Risk Analytics, Digital Twin Learning Models, and Continuous Learning Pipelines.

Required Skills

Strong expertise in Knowledge Graphs, Vector Databases, machine learning, Reinforcement Learning, Retrieval-Augmented Generation (RAG), data science, Python programming, and AI knowledge systems.