Senior Software Engineer, Machine Learning

Company: Singular Genomics
Location: Lemon Grove
Posted on: June 25, 2022

Job Description:

ABOUT SINGULAR GENOMICS

Singular Genomics is inventing at the forefront of genomics, one of the world's fastest-growing industries. We are a publicly traded life science technology company that is leveraging novel, next generation sequencing (NGS) and multiomics technologies to build products that empower researchers and clinicians. Our novel Sequencing Engine is the foundational technology that drives Singular Genomics' products in development and our core product tenets: power, speed, flexibility and accuracy.

We are passionate about the promise of genomics to improve human health and are committed to making it a reality. We offer a dynamic, fast-paced, results-oriented environment where employees can make a significant impact in a rapidly expanding company. Innovation, continuous learning, and multi-disciplinary collaboration are pillars of our culture.

We are in La Jolla, California at the center of the biotech hub on the Torrey Pines Mesa close to the Pacific Ocean-next door to prestigious institutions like the Salk Institute, Scripps Research Institute, Sanford Burnham and UCSD.

Position Summary:

The Machine Learning team at Singular Genomics is responsible for delivering models that run on our sequencers to help convert raw data into genomic sequence predictions. The Senior Software Engineer, Machine Learning role requires you to develop machine learning software to accelerate iteration, evaluation, and deployment of our models. We're a small team looking for someone excited to help us create a data engineering vision for the company and contribute to building it. We're based out of San Diego, CA, however, this position allows for remote work.

What you'll be doing:

Developing and maintaining scalable and reliable machine learning software to ease iteration, evaluation, and deployment of machine learning models across the company.
Implementing large-scale data ecosystems including data management, governance, and the integration of structured and unstructured data (on the order of 10s of terabytes) to allow our team to efficiently train models, track improvements over time, and monitor deployed models.
Helping to shape the direction/architecture of our data engineering.
Using statistical and machine learning techniques to create efficiently deployable ML models and then deploy and monitor them.
Explaining and documenting model behavior/results to both technical and non-technical audiences.
Collaborating with machine learning scientists, software engineers and a multi-disciplinary team of scientists.
Staying current on new products, papers, and industry trends in the field of machine learning. Our team values continual growth and reserves a portion of each week for individual projects (e.g. learning a new language/framework, auditing an online course, hacking on a new dataset).

Who you are and your background:

You're a team player. You enjoy collaborating with and learning from experts in other fields (e.g. biology, bioinformatics, physics).
You're experienced at building machine learning pipelines. You're excited by the opportunity to take prototypes and help scale them up into products.
You're excited to contribute to machine learning applications in the biological sciences.
You're proficient in Python and have experience building models in PyTorch and/or TensorFlow.
You've worked with large datasets and understand the tradeoffs between different data storage and management technologies and models (SQL, NoSQL, columnar databases, AWS/GCP, data lake, data warehouse).
You've built tools for data extraction, transformation, and loading (SQL/ETL, Python, etc.) for datasets.
You have experience with modern software engineering tools such as Git, CI/CD, and containerization.
You have a Bachelor of Science in a quantitative field (e.g. Computer Science, Physics, Engineering, Math) as well as at least 3-5 years of industry experience.

Nice-to-Haves:

Understanding and experience with building front-end visualizations for analytics and validating models.
Experience using GPUs and/or FPGAs as accelerators for machine learning applications.
Knowledge of C++ and how it can be applied to ML infrastructure optimization.
Advanced degree (M.S. or Ph.D.) in a quantitative field (e.g. Computer Science, Physics, Engineering, Math).

Please be aware that, as a condition of employment, Singular Genomics requires proof of COVID vaccination for all employees (subject to limited exceptions) beginning November 1, 2021.

Singular Genomics is an equal opportunity employer. We celebrate diversity and are committed to creating an inclusive environment for all employees.

Keywords: Singular Genomics, San Diego , Senior Software Engineer, Machine Learning, IT / Software / Systems , Lemon Grove, California