Research Engineer: Machine Learning and Knowledge Representation for Biodata

Research Engineer: Machine Learning and Knowledge Representation for Biodata

Location: Dublin, Ireland

Team: Accenture Labs Bioinnovation

Level: CL8

Type: Full-time, on-site (hybrid)

About: This is an opportunity to play a key role in the Accenture Labs BioInnovation team, in Dublin Ireland.

Accenture Labs BioInnovation is the biotech research arm of Accenture Labs and focuses on Artificial Intelligence, Bioinformatics, and Computational Chemistry with a strong emphasis on Machine Learning for life sciences.

The lab is co-located with The Dock, Accenture's global center for innovation.

We design and prototype new ideas that have a strategic impact on our clients’ businesses. We offer a blend of industry-related research projects and academic-oriented activities, including an open publication policy and contribution to the open-source community.

Job Description:

Design and implement AI research prototypes for the life sciences, including genomic medicine and computational chemistry.

Collaborate with research scientists and engineers to turn experimental methods and their output into full-fledged prototypes to showcase the impact of our research.

Develop and implement machine learning models for de novo molecule generation, and property prediction (small molecules and biologics)

Design and optimize deep learning architectures for molecular generation and optimization (e.g., graph machine learning, transformers, diffusion models).

Design and implements prototypes to learn insights from multi-omics data (e.g. genomics, transcriptomics, proteomics).

Build data ingestion pipelines to process and analyze large-scale biochemical and multi-omics datasets (e.g., SMILES, PDB, proteomics, genomics, clinical records).

Collaborate with subject matter experts to integrate domain knowledge into our AI models and interpret results.

Stay on top of the latest advancements in AI/machine learning, AI for drug discovery, computational chemistry, and bioinformatics.

Write clean, well-documented code.

Required qualifications and skillset:

MSc in Computer Science, Computer Engineering, Bioinformatics, Computational Biology, Computational Chemistry, Computational Genomics, or equivalent industry experience.

Strong Machine Learning and Deep Learning foundations.

Solid Python and Scientific Python programming skills (e.g. NumPy) and Machine Learning frameworks such as PyTorch.

Prior hands-on experience with AI/ML research prototypes design and development

Proven knowledge of parallel computing techniques for Python and GPU acceleration, to optimize model training and data processing workflows.

Solid experience with data engineering, data ingestion, relational databases management, SQL.

Practical experience with LLMs (frontier API-based and self-hosted/open-weight), including retrieval-augmented generation and in-context learning, PEFT (e.g., LoRA/QLoRA), and building agentic workflows.

Working knowledge of Linux OS, shell scripting

Hands-on experience with git and popular issue tracking systems

Ability to work creatively and analytically in a problem-solving environment

Eagerness to contribute to a team-oriented environment

Excellent verbal and written communication in English

Optional skillset:

Familiarity with Knowledge Graph technologies a plus, but not a hard requirement (e.g. RDF, RDFS/OWL, SPARQL, triplestores).

Hands-on experience with workflow orchestration tools (e.g., Prefect) for building ML and data pipelines.

Familiarity with common genomic data formats (e.g., FASTQ, VCF).

Experience processing Electronic Health Record (EHR) datasets.

Expertise in back-end development (e.g. Django, Flask)

Previous contributions to open-source projects in the machine learning, bioinformatics or computational chemistry space.