Deep Genomics is at the forefront of using artificial intelligence to transform drug discovery. Our proprietary AI platform decodes the complexity of RNA biology to identify novel drug targets, mechanisms, and therapeutics inaccessible through traditional methods. With expertise spanning machine learning, bioinformatics, data science, engineering, and drug development, our multidisciplinary team is revolutionizing how new medicines are created.
Role Overview
- Position: Machine Learning Research Engineer
- Locations: Toronto, ON or Cambridge, MA (Kendall Square)
- Environment: Collaborative and multidisciplinary, blending computational and wet-lab sciences
We are looking for a research engineer who bridges the gap between fast-paced, experimental academic ML research and robust production systems. You possess a solid mathematical foundation and a deep understanding of modern ML architectures, combined with the technical skills to write clean and highly optimized PyTorch code. You take pride in creating core tooling that empowers research teams to move fast without breaking everything.
Key Responsibilities
- Core Tooling & Infrastructure: Build and maintain the engineering infrastructure that allows the research team to iterate rapidly and safely. Owns "Build vs. Buy" and open-source adaptation strategies that shape the 1–2 year technical roadmap.
- Bridge Research & Engineering: Refactor, optimize, and add engineering rigor to messy, script-like experimental research code without stifling discovery. Establish team-wide guardrails, templates, and mentor researchers on engineering best practices.
- Model Implementation: Implement, train, and evaluate modern deep learning architectures from scratch using PyTorch. Successfully translate dense, math-heavy research papers into functional software.
- Testing & Troubleshooting: Rigorously test and troubleshoot complex ML systems to ensure both software correctness and optimal computational efficiency. Formulate hypotheses to independently diagnose convergence issues and data bottlenecks.
- Cross-Functional Collaboration: Partner closely with dedicated MLOps and Data Engineering teams to seamlessly transition research models into existing production pipelines.
Qualifications
Basic Qualifications
- Mathematics: Solid foundational grasp of linear algebra, calculus, and probability.
- Deep Learning: Strong understanding of modern machine learning/deep learning architectures and training dynamics.
- PyTorch Proficiency: Highly proficient in PyTorch, including model building and basic optimization.
- Software Engineering: Strong general programming skills, with practical experience handling concurrency, threading, memory management, and debugging.
- Ambiguity Tolerance: High tolerance for ambiguity and a willingness to work hands-on with unstructured, messy research scripts.
Preferred Qualifications
- Advanced PyTorch & Infrastructure: Extensive knowledge of PyTorch internals, distributed training paradigms, custom operators (e.g., CUDA/Triton kernels), and advanced performance profiling.
- Mangement & Strategy: Experience managing large-scale data pipelines and partnering with MLOps.
- Tooling: Familiarity with ML experiment tracking tools (e.g., Weights & Biases), workflow orchestration (e.g., Airflow), Kubernetes, and containerization (Docker) on cloud platforms (e.g., GCP).
- Domain Interest: Domain knowledge or a strong interest in computational biology (prior biology expertise is not required).
What You'll Gain & Impact
- Direct Patient Impact: Your engineering work will directly impact the creation of new genetic medicines for patients with unmet needs.
- Foundation Models: The opportunity to build Biological Foundation Models that map genetic inputs to downstream molecular mechanisms and patient outcomes.
- Scientific Immersion: Partner with computational biologists and wet-lab scientists, gaining the deep scientific context needed to maximize your engineering impact.
- Publications: Opportunities to publish and present work focusing on AI for genome biology and medicine.
What We Offer
- Compensation: Highly competitive compensation, including meaningful stock ownership.
- Comprehensive Benefits: Health, vision, and dental coverage for employees and families, alongside an employee and family assistance program.
- Flexibility & Time Off: Flexible work environment (including flexible hours), extended long weekends, holiday shutdown, and unlimited personal days.
- Family Support: Maternity and parental leave top-up coverage, as well as new parent paid time off.
- Growth: Learning and development budget alongside regular educational lunch-and-learns.
