MOLCURE Co., Ltd.
- Job Type
- Bioinformatics Scientist — Antibody Discovery & NGS
[The Role]
We are looking for a Bioinformatics Scientist who will work across the full spectrum of antibody discovery—from mining screening data to computationally designing new candidate sequences. Working at the forefront of our antibody discovery engine, you will own the end-to-end NGS analysis pipeline, partner directly with wet-lab scientists to close the loop between computation and experiment, and collaborate with ML engineers to apply generative AI approaches for sequence design and optimization.
This is not a downstream analysis role. You will shape which candidates enter our optimization pipeline—whether discovered from screening data or computationally designed—and your biological interpretation will directly influence lead selection decisions. As an early member of the computational team, you will have the autonomy to define how our discovery informatics evolves.
[Position Overview]
We are seeking a Bioinformatics Scientist who will work across the entire spectrum of antibody discovery, from mining screening data to designing novel candidate sequences using generative AI. This role is at the forefront of antibody discovery engines, offering end-to-end ownership of the NGS analysis pipeline. You will work directly with wet lab scientists to close the computation-experiment loop, and collaborate with ML engineers to drive generative AI approaches to sequence design and optimization.
This is not downstream analysis work. You will determine which molecules enter the optimization pipeline, whether candidates discovered through screening or computationally designed, and your biological interpretations will directly impact lead selection decisions. As an early member of the computational team, this position offers autonomy, allowing you to define the direction of discovery informatics evolution.
What You Will Do
• NGS Pipeline Development & Execution
Build, execute, and continuously refine pipelines for processing high-throughput sequencing data from antibody display and screening campaigns. Ensure reproducibility, scalability, and rapid turnaround to keep pace with experimental cycles.
• Candidate Discovery & Prioritization
Analyze clonal enrichment, sequence diversity, and predicted developability to identify and rank antibody leads. Provide data-driven rationale for which candidates advance to downstream characterization.
• AI-Driven Sequence Design
Collaborate with ML engineers to leverage generative AI and protein language models for de novo antibody sequence design and optimization. Evaluate computationally designed candidates using the same biological and developability criteria applied to screening-derived hits, bridging the gap between generative models and experimental validation.
Wet-Lab Partnership
Serve as the primary computational partner to bench scientists. Interpret screening results collaboratively, provide rapid feedback on experimental outcomes, and co-design iterative screening strategies based on data insights.
• Pipeline & Codebase Evolution
Maintain and improve our Python-based analysis codebase. Architect flexible, modular systems that can incorporate new algorithms, public datasets, and evolving experimental formats as the field advances.
• Scientific Intelligence
Monitor the rapidly evolving landscape of AI-driven antibody discovery and NGS methodology. Evaluate emerging tools and approaches, and bring validated improvements into our production workflows.
[Responsibilities]
• NGS Pipeline Development and Execution
Build, execute, and continuously improve pipelines that process high-throughput sequencing data obtained from antibody display and screening campaigns. Ensure reproducibility, scalability, and rapid turnaround to keep pace with the experimental cycle.
• Candidate Antibody Discovery and Prioritization
Analyze clonal enrichment, sequence diversity, and predicted development potential to identify and rank antibody leads. Provide data-driven rationale for which candidates should proceed to downstream characterization.
• AI-Powered Sequence Design
Collaborate with ML engineers to drive de novo antibody sequence design and optimization using generative AI and protein language models. Computationally designed candidates are evaluated using the same biological and developmental feasibility criteria as screening-derived hits, bridging the gap between generative models and experimental validation.
• Wet Lab Collaboration
Serving as a primary computational partner for bench scientists. Collaboratively interpreting screening results, providing rapid feedback on experimental results, and co-designing data-insight-based, iterative screening strategies.
• Pipeline Codebase Evolution
Maintaining and improving the Python-based analysis codebase. Designing a flexible and modular system that can accommodate new algorithms, public datasets, and evolving experimental formats.
• Scientific Intelligence
Monitoring the rapidly evolving trends in AI-driven antibody discovery and NGS methodologies. Evaluating emerging tools and approaches and introducing validated improvements into production workflows.
