Retrosynthesis Researcher, Machine Learning

Schrdinger; New York (NY); On-site; USD 120,000 - 145,000; Full time

Benefits offered by this job

Healthcare (with dental and vision)

401k

Flexible work schedule

Parental leave

Job summary

Schrödinger is seeking a Retrosynthesis Researcher in Machine Learning (ML) to transform therapeutic and material discoveries. The role involves developing AI/ML models for predicting retrosynthetic pathways and collaborating with chemists to validate outcomes. This position is based in New York, where the company offers a competitive salary range of $120,000 - $145,000 depending on qualifications.

Integral to this role is a PhD in Chemistry or a related field, along with expertise in organic synthesis. Schrödinger fosters a culture of diversity and engagement and offers a range of benefits including healthcare, 401k, and paid vacation.

Qualifications

• PhD in Chemistry, Computational Chemistry, Cheminformatics, or a related field.
• Solid publication record in retrosynthesis and computational chemistry.

Responsibilities

• Develop and implement AI/ML models for retrosynthetic pathway prediction.
• Apply deep learning techniques to predict reaction outcomes and optimize conditions.
• Curate and manage reaction datasets to train predictive models.
• Collaborate with chemists for validating predicted pathways.

Skills

Machine Learning

Cheminformatics tools

Python programming

Organic synthesis

Education

PhD in Chemistry or related field

Tools

Pytorch

Tensorflow

JAX

Job description

Schrödinger seeks a Retrosynthesis Researcher in Machine Learning (ML) to join us in our mission to transform the discovery of therapeutics and materials.

Schrödinger has pioneered a physics-based software platform that enables discovery of high-quality, novel molecules for drug development and materials applications more rapidly and at lower cost compared to traditional methods. The software platform is used by biopharmaceutical and industrial companies, academic institutions, and government laboratories around the world. Our multidisciplinary drug discovery team also leverages the software platform to advance collaborative programs and its own pipeline of novel therapeutics to address unmet medical needs.

Who will love this job:

• An ML expert who has applied AI tools to chemical reaction prediction or retrosynthesis (e.g., reaction templates, template-free approaches) and understands organic synthesis and reaction mechanisms
• An experienced user of cheminformatics tools (e.g., RDKit, Open Babel)
• A proficient Python programmer who’s familiar with ML tools like Pytorch, Tensorflow, and JAX
• An excellent problem-solver who’s comfortable working collaboratively in a multidisciplinary research environment

What you’ll do:

• Develop and implement AI/ML models (e.g., graph neural networks, transformer-based models) for retrosynthetic pathway prediction
• Apply deep learning techniques to predict reaction outcomes, optimize reaction conditions, and identify novel synthetic routes
• Curate and manage reaction datasets from literature, patents, and proprietary sources to train and validate predictive models
• Integrate retrosynthesis tools with cheminformatics platforms and molecular modeling software
• Collaborate with synthetic chemists to experimentally validate predicted retrosynthetic routes and optimize laboratory workflows
• Contribute to scholarly publications in high-impact journals and represent the research group in conferences and workshops

What you should have:

• PhD in Chemistry, Computational Chemistry, Cheminformatics, or a related field
• A solid publication record that demonstrates expertise in retrosynthesis algorithms and computational chemistry

We’d prefer to hire someone who has:

• Familiarity with chemical reaction databases (e.g., Reaxys, USPTO, Pistachio)
• Knowledge of computer-aided synthesis planning (CASP) tools and retrosynthetic analysis software (e.g., AiZynthFinder, ASKCOS, IBM RXN)
• A background in graph-based learning, attention mechanisms, and transformer architectures applied to chemical data
• Familiarity with reaction condition prediction and reaction yield optimization.
• Experience with Schrödinger Suite and LiveDesign
• Experience with de novo design and generative machine learning methods
• Experience with cloud computing and/or high-performance computing (HPC) resources
• Exposure to quantum chemistry (DFT) is a plus

Pay and perks:

Schrödinger understands it’s people that make a company great. Because of this, we’re prepared to offer a competitive salary, equity-based compensation, and a wide range of benefits that include healthcare (with dental and vision), a 401k, pre-tax commuter benefits, a flexible work schedule, and a parental leave program. We have regular catered meals in the office, a company culture that is relaxed but engaged, and over a month of paid vacation time. Our Office Management team also plans a myriad of fun company-wide events. New York is home to our largest office, but we have teams all over the world. Schrödinger is honored to have been included in Crain's New York Best Places to Work, BuiltIn's NYC Best Place to Work, and Newsweek's list of America's 100 Most Loved Workplaces.

Estimated base salary range: $120,000 - $145,000. Actual compensation package is dependent on a number of factors, including, for example, experience, education, degrees held, market data, and business needs. If you have any questions regarding the compensation for this role, do not hesitate to reach out to a member of our Strategic Growth team.

As an equal opportunity employer, Schrödinger hires outstanding individuals into every position in the company. People who work with us have a high degree of engagement, a commitment to working effectively in teams, and a passion for the company's mission. We place the highest value on creating a safe environment where our employees can grow and contribute, and refuse to discriminate on the basis of race, color, religious belief, sex, age, disability, national origin, alienage or citizenship status, marital status, partnership status, caregiver status, sexual and reproductive health decisions, gender identity or expression, sexual orientation, or any other protected characteristic. To us, "diversity" isn't just a buzzword, but an important element of our core principles and key business practices. We believe that diverse companies innovate better and think more creatively than homogenous ones because they take into account a wide range of viewpoints. For us, greater diversity doesn't mean better headlines or public images - it means increased adaptability and profitability.