(Senior) Research Scientist - Large Language Models for Genomics at Deep Genomics

Toronto, Ontario, Canada

Apply Now

Not SpecifiedCompensation

Mid-level (3 to 4 years)Experience Level

Full TimeJob Type

UnknownVisa

Biotechnology, Artificial IntelligenceIndustries

Requirements

Master's or Ph.D. in Computer Science, Computational Biology, Bioinformatics, or a related field
3+ years of hands-on experience architecting and building complex applications using Large Language Models
Expert knowledge of Python and modern MLOps frameworks and tools
Experience with agentic frameworks like LangChain is essential
Demonstrated experience in building multi-agent systems that can plan, execute tasks, and interact with external tools and APIs
Familiarity with high-performance computing environments and cloud services (e.g., AWS, GCP)
Excellent communication skills and ability to work effectively in a multidisciplinary team
Intellectual curiosity, critical thinking, and commitment to innovation and scientific rigor
Strong background in genomics, computational biology, or bioinformatics, including experience with NGS data analysis or large-scale biological datasets
Prior experience in the biotech or pharmaceutical industry, particularly in a drug discovery context
Experience with model distillation or creating smaller, specialized models from larger foundation models
Familiarity with scientific workflow management systems and tools

Responsibilities

Design and implement multi-agent workflows that integrate internal foundation models (e.g., BigRNA, REPRESS, FlashRNA) and external tools to identify new biological hypotheses
Develop systems that leverage Retrieval Augmented Generation (RAG) by connecting LLMs to internal scientific documents, SOPs, and structured biological databases
Collaborate with the machine learning team on model distillation strategies to create smaller, faster models suitable for a real-time, interactive chat interface
Build out and maintain the infrastructure for the LLM agent, including databases and model context protocol (MCP) endpoints
Work closely with end-users in therapeutic design, target discovery, and experimental biology to identify key use cases, gather feedback, and rapidly iterate on the product
Ensure the system is transparent and trustworthy by building "explainable AI" features that help users understand and verify the AI's outputs and decisions

Skills

Key technologies and capabilities for this role

Large Language Models (LLMs)GenomicsComputational BiologyMLOpsRetrieval Augmented Generation (RAG)Multi-agent workflowsSystem DesignScientific Computing

Questions & Answers

Common questions about this position

What qualifications are required for this role?

Candidates need an MSc or PhD in Computer Science, Computational Biology, Bioinformatics, or a related field, plus 3+ years of hands-on experience architecting and building complex applications using Large Language Models, along with expert knowledge of Python and modern MLOps frameworks.

What experience is the ideal candidate expected to have?

The ideal candidate has 3+ years of experience in using and developing solutions using LLMs for complex, multi-agent workflows, a background in genomics or computational biology, and clear experience in MLOps and architecting agentic solutions.

Where are the company's offices located?

The multidisciplinary team is based in Toronto and Cambridge, MA.

What teams will I collaborate with in this role?

You will interact closely with the machine learning team developing foundation models, the engineering and infrastructure teams to build scalable systems, and the statistical genetics and experimental groups, while working within the Systems and Target Biology group.

What makes a strong candidate for this position?

A strong candidate is passionate about leveraging AI and foundation models to disrupt therapeutic design workflows, adept at translating complex scientific requirements into robust computational solutions, and has a background in genomics or computational biology.

Deep Genomics

AI-driven drug discovery and development

About Deep Genomics

Deep Genomics focuses on drug development in the biotechnology sector by utilizing artificial intelligence to explore RNA biology and discover potential therapies for genetic conditions. The company's main product, the AI Workbench, employs data-driven predictions to identify new drug targets. This tool has evolved over time, with the latest version, AI Workbench 3.0, set to enhance its capabilities in targeting complex genetic diseases. Deep Genomics serves a diverse clientele, including pharmaceutical companies and research institutions, and generates revenue through the development and licensing of its AI Workbench. The goal of Deep Genomics is to accelerate the drug discovery process and improve treatment options for patients suffering from genetic disorders.

Toronto, CanadaHeadquarters

2014Year Founded

$230.3MTotal Funding

SERIES_CCompany Stage

AI & Machine Learning, BiotechnologyIndustries

51-200Employees

Benefits

Company Equity

Health Insurance

Dental Insurance

Vision Insurance

Life Insurance

Disability Insurance

Professional Development Budget

Risks

Increased competition from companies like Insitro and Recursion Pharmaceuticals.

Rapid technological advancements may render current AI Workbench obsolete.

Ethical concerns and regulatory scrutiny could delay product development timelines.

Differentiation

Deep Genomics uses AI to unravel RNA biology for drug development.

The AI Workbench identifies novel drug targets and therapeutic candidates.

BigRNA model advances RNA disease mechanism discovery and candidate therapeutics.

Upsides

AI integration with CRISPR allows precise gene editing and therapeutic development.

AI-driven platforms optimize clinical trial designs, reducing costs and time to market.

AI identifies novel biomarkers, expanding target discovery capabilities.

Land your dream remote job 3x faster with AI

Try Jobo Free