Software Engineer

At Epimethyl Analytics, we seek to hire a software engineer or computer programmer to support advanced computational technologies in a healthcare-focused environment.  The company's mission centers on advancing preventative healthcare by decoding genomic data to facilitate interventions before symptoms are evident, thereby improving treatment outcomes and quality of life.

The company offers a comprehensive platform for health insights applicable across various life stages, targeting partnerships with medical centers, pharmaceutical firms, and other providers to enhance diagnostics, drug discovery, and treatment protocols. This proprietary platform integrates signal detection, machine learning, and cloud computing to process genomic data and enable applications in diagnostics for several health conditions.

Salary will be commensurate with experience and skill level. Expert mentors will support your career growth. Together, we'll help you achieve meaningful goals and make a positive impact locally and globally. If you're ready for the challenge, we want you on our team.

Minimum qualifications

• Bachelor's, Master's or PhD degree in computational sciences, such as computer science, data science, electrical engineering, mathematics, bioinformatics, or related discipline.
• Previous experience in computer programming, particularly in Python GPU computation and cloud computing.
• U.S. citizen / Green card holder

Core Technical Skills

The expected skills align with high-demand roles in data science, AI, and high-performance computing, where GPU-accelerated Python workflows on cloud infrastructure are increasingly prevalent. Candidates with hands-on experience through projects or certifications (e.g., AWS Certified Machine Learning, Google Professional Machine Learning Engineer) would be particularly competitive.

·      
Advanced Proficiency in Python Programming
: Strong command of Python fundamentals, including object-oriented programming, scripting, and optimization techniques. This forms the foundation for implementing vectorized computations and integrating with specialized libraries.

·      
Vectorization and Numerical Computing
: Expertise in libraries like NumPy for efficient array operations and vectorized processing, which is essential for handling large datasets without explicit loops. Familiarity with SciPy for advanced mathematical functions would further enhance performance in data analysis.

·      
GPU Acceleration and Parallel Computing
: Knowledge of GPU programming frameworks such as CUDA (via PyCUDA or Numba), cuML and CuPy for Python-based vectorized computations on GPUs. This skill is critical for speeding up matrix operations and simulations, particularly in machine learning workloads.

·      
Machine Learning Frameworks
: Proficiency in libraries like TensorFlow, PyTorch, or scikit-learn, with a focus on GPU-enabled implementations for training models efficiently. Understanding of neural networks, deep learning architectures, and model optimization is necessary for integrating ML into data pipelines.

·      
Data Analysis and Manipulation
: Skills in Pandas for data wrangling, cleaning, and exploratory analysis, complemented by statistical knowledge for hypothesis testing and inference. Visualization tools such as Matplotlib or Seaborn should be included to interpret results effectively.

·      
Cloud Computing and Deployment
: Experience with cloud platforms such as AWS (e.g., EC2 GPU instances, SageMaker), Google Cloud Platform (e.g., Compute Engine with TPUs/GPUs, Vertex AI), or Azure (e.g., Virtual Machines, Azure Machine Learning) for provisioning powerful machines, managing scalable resources, and deploying Python-based applications. Knowledge of containerization (Docker) and orchestration (Kubernetes) would support efficient cloud implementations.

·      
Distributed and Big Data Processing
: Familiarity with tools like Dask or Apache Spark (integrated with Python via PySpark) for handling large-scale data across cloud clusters, ensuring seamless transition from local GPU computations to distributed environments.

Complementary Skills

·      
Mathematical and Statistical Foundations
: Solid understanding of linear algebra, calculus, probability, and statistics, which underpins vectorized GPU operations, machine learning algorithms, and data analysis.

·      
Software Engineering Practices
: Version control with Git, testing frameworks (e.g., pytest), and agile methodologies to maintain code quality in collaborative projects.

·      
Problem-Solving and Analytical Abilities
: Capacity to optimize algorithms, debug complex systems, and adapt to evolving data requirements, ensuring practical application of technical skills.

Expected Responsibilities

·      
Developing and optimizing machine learning algorithms
for analyzing large-scale genomic datasets (including neural network) and potentially involving unsupervised learning techniques to identify patterns in DNA methylation.

·      
Building scalable data pipelines and cloud-based infrastructure
to handle complex biological data, ensuring efficient processing and integration with medical applications.

·      
Collaborating with interdisciplinary teams
, including biologists and data scientists, to translate research needs into robust software solutions for diagnostics, drug discovery, and personalized medicine protocols.