Benjamin Rizkin, PhD

What I do

Benjamin Rizkin is a chemical engineer working in pharmaceutical CMC, chemistry, manufacturing and controls, and technical operations: the part of drug development that turns a molecule into a process a regulator will license and a plant can run. Route design and scale-up, formulation, analytical development, IND and IMPD content, clinical supply through Phase 3, process characterization and validation, Module 3, pre-license inspection readiness, and commercial supply.

The second half of the practice is data. I have trained machine learning models for molecular design and process optimization, and I have also had to explain a computerized system to an inspector, which is an unusual pair of experiences to find in one person and is most of what makes the work useful. Data architecture and integrity, manufacturing and quality analytics, models for molecules and processes, and the qualification that lets any of it be used for a decision a regulator can ask about.

In short

Training

PhD, chemical engineering. New York University and the University of Massachusetts Amherst.

Field

Pharmaceutical CMC and technical operations. Data, analytics and machine learning for the same industry.

Modalities

Small molecules, peptides, antibody drug conjugates and bioconjugates, biologics, autologous cell therapy, and a drug-device combination product.

Research

Nine publications, first author in Nature Machine Intelligence. Inventor on six patent filings across ten jurisdictions. ORCID.

Based

Winston-Salem, North Carolina. Works with clients worldwide.

Practice

Rizkin Labs LLC. Consulting engagements, and open to senior technical operations and CMC leadership roles.

Programs and record

Adrabetadex, a sterile intrathecal therapy for Niemann-Pick Type C, owned end to end through three CDMOs. Rilparencel, an autologous cell therapy in Phase 3 under RMAT, through pivotal execution into BLA and pre-license inspection readiness. Venclexta, Rinvoq and Vyalev on the approved side. Navitoclax and ABBV-154 through late-stage validation and PPQ. ABBV-155, ABBV-484 and ten further molecules from preclinical into the clinic.

A dual-facility commercial build guided from design through qualification. An AI and machine learning platform for molecular design and process optimization, selected for the NVIDIA Inception program. Six patents and applications across ten jurisdictions, covering enzymatic cyclodextrin production and modular manufacturing.

Things I have published here

• Pharma acronyms and guidance finder. Every ICH guideline, the 21 CFR parts that come up, the EU GMP annexes, USP general chapters, PDA technical reports and close to seven hundred acronyms. 1,006 entries, searchable, free.
• Certificate of analysis and specification builder. Describe a drug product and it returns the release specification and a printable certificate of analysis: 121 tests, 21 modalities, 12 pharmacopoeial regions.
• AI under GMP. Where the draft EU Annex 22, the revised Annex 11 and the FDA credibility framework stand, and what to build before any of them is final.
• Field guides. Quality by Design, the analytical procedure lifecycle, the integrated CMC roadmap, and running a CMC program.
• The Bench. Fourteen working instruments, hand written, no frameworks.

Getting in touch

Engagements run through Rizkin Labs LLC: fractional head of CMC, an external network built or repaired, filing and inspection readiness, technical diligence for a raise, a data estate nobody can join, or a site that is not running right. I am also open to a permanent senior technical operations or CMC seat. Either way the first conversation is free, and I will tell you if I am the wrong person for it.