-
Job Description
Company Description:
FluidAI Medical is creating a paradigm shift in post-operative care, utilizing the plethora of data within the body, to help in the detection of post-operative complications at their onset. Our clinically validated platform sensing technology augments existing wound drains and catheters, providing healthcare providers with a smart monitoring tool that can support earlier detection of deadly complications and enhance the delivery of care.
We are an equal opportunity employer and have a diverse team representation across language, ethnicity, gender and nationality.
Why join FluidAI Medical?
- Mission to save lives and improve patient care with revolutionary technology that’s already deployed on patients in real-world settings.
- Work with a high-performing and cross-functional team that is empowered to grow, learn, and contribute across all levels of the organization.
- We are a team of passionate builders and boundary-breakers that are on a singular mission to disrupt how patient care is done. We aim to succeed and perform together - as a team and as individuals.
- Gain exposure across the entire technical stack, from novel sensing technologies and proprietary hardware to mobile/web software and ML algorithms.
- Personal career-focused development and training with access to workshops, coursework, and experienced mentors/consultants.
Job Description:
We're looking for someone with a strong foundation in data engineering to build and maintain data pipelines that drive downstream Machine Learning (ML) and Analytics. As part of this role, you will work collaboratively with our software, hardware, clinical, and R&D teams to democratize data access throughout the organization.
You’ll be living and breathing clinical study, device biosignal and Electronic Health Records (EHR) datasets, regularly wrangling new and old data in new ways, developing reliable and scalable data processing pipelines, and testing these pipelines systematically to ensure high integrity data quality.
You’ll be the owner of our proprietary device and EHR datasets, and ensure our data lakehouse (we are a Databricks shop) is setup to allow iterative and robust development, while ensuring data governance policies are implemented and adhered to across the organization.
It's not everyday that you get a chance to make a direct impact on people's health. If you're looking to join a strong tight knit team for a meaningful product, this is for you!
This is an office-first role working out of our Kitchener HQ in the Medical Innovation Xchange.
Responsibilities:
- You will design scalable and robust data architectures with traceable “single source-of-truth” datasets whilst adhering to formal data engineering practices
- We ingest data from our device and EHRs; you will have to build and maintain end-to-end (ingestion, storage, transformation and serving) data pipelines
- When working with clinical data, especially Real World Data (RWD), data quality is of utmost importance. You will have to implement quality standards and automated checks for both clinical and biosignal data.
- You get to be the gatekeeper of our data. You have to help different teams make the most of our data by creating secure ways for them to access the data.
Qualifications:
- 2+ years hands on data engineering experience
- You have a solid understanding of data engineering lifecycle
- You are proficient in Python
- You are an expert in manipulating datasets in either Pandas, PySpark, or Polars
- You are comfortable querying data with SQL (queries, joins, window functions and views)
- You should have production-grade software engineering chops
- You have excellent technical communication skills - you get excited about writing documentation
Bonus Qualifications:
These are the skills and competencies we are looking for in an ideal candidate. If you check some but not all these boxes, please apply anyway
Domain
- You have experience working with messy Real World Data (RWD) - EHR (clinical notes, flowsheets, etc) or claims data
- You have experience working with common data models like ODHSI OMOP CDM
- You are familiar with medical coding standards (e.g. HCPCS, ICD9/10, CPT, SNOMED, LOINC, RxNorm and NDC)
- You are familiar with EHR standards like HL7 FHIR
- You are familiar with HIPPA and GDPR
Technical
- You have experience working with Snowflake or Databricks
- You have build batch processing pipelines using Spark
- You are familiar with DevOps and DataOps practices
- You have worked closely with ML teams for model training and model deployment at a production scale
- These are the skills and competencies we are looking for in an ideal candidate. If you check some but not all these boxes, please apply anyway
Application Process:
- Introductory Phone Call (~15 Minutes)
- Technical Coding Interview (45-60 Minutes)
- Second Technical Panel Interview (45-60 Minutes)
- Offer Stage
If you are passionate about ensuring software excellence and driven to lead quality advancements in the healthcare industry, we would love to hear from you!
#J-18808-Ljbffr