** Federal Project - Applicant must be a United States Citizen, with the ability to obtain a Public Trust. **
Baer is looking for a Data Scientist for a 9-month Federal project located in Baltimore, MD.
Title: Data Scientist Location: Remote and Baltimore, MD (Future Onsite) Duration: 9 months Rate: All-inclusive Alignment: W2 or C2C (Vendors Not Permitted)
Description:
Formulate, design, and deliver AI/ML-based decision-making frameworks and models to achieve business outcomes.
Develop and fine-tune AI models for NLP tasks, including Named Entity Recognition (NER), text classification, and sentiment analysis with a focus on unstructured clinical data.
Analyze and preprocess large datasets, particularly unstructured medical records (e.g., physician notes, discharge summaries) using tools like Pandas, NLTK, and SpaCy.
Create custom NLP algorithms and annotators for extracting insights from medical records.
Work with human-in-the-loop systems, incorporating clinician feedback to refine and improve AI models.
Conduct experiments to evaluate AI model performance, employing metrics such as precision, recall, and F1-score.
Collaborate with cross-functional teams, including software engineers, to ensure AI solutions are integrated into the broader system architecture.
Create custom tools to enable analysts to perform data research.
Maintain comprehensive technical documentation and provide ongoing system support.
Develop data pipelines for efficient data processing, integrating with databases such as SQL (PostgreSQL, MySQL) and NoSQL (MongoDB, Elasticsearch).
Deploy AI models using cloud platforms (AWS, Azure) and containerization technologies like Docker, and manage them using CI/CD pipelines.
Requirements:
5+ years of experience in AI/ML development, with a strong focus on NLP using frameworks such as TensorFlow, PyTorch, and Hugging Face.
Mastery in Python frameworks and libraries like Transformers, NLTK, SpaCy, Gensim, and data manipulation tools such as Pandas and NumPy.
Proven experience with human-in-the-loop systems that incorporate clinician feedback to improve model performance.
Experience with cloud platforms (AWS, Azure), containerization (Docker), and CI/CD pipelines for machine learning model deployment.
Solid understanding of statistical modeling, data analysis, and performance evaluation metrics.
Expertise in analyzing and processing unstructured clinical data using techniques such as tokenization, lemmatization, and word embeddings (e.g., TF-IDF, BERT).
Knowledge of healthcare data formats and standards such as HL7, FHIR, ICD codes, and SNOMED.
Ability to effectively articulate technical challenges and solutions, with excellent written and verbal communication skills.
Familiarity with SQL and NoSQL databases and structuring data pipelines for efficient processing.
Master's degree in Data Science, AI, Computer Science, or a related field + 10 years of experience; or PhD + 4 years of experience.
Public Trust Security Clearance is the lowest level of additional background screening that the federal government requires for applicants of certain jobs, which includes completing a form.
Company Overview:
Baer is an Enterprise Performance Partner providing job opportunities with several 1st Tier Global Systems Integrators and a wide array of Fortune 1000 clients. Baer consultants and employees enjoy access to the highest profile job opportunities across leading Enterprise Technology Solutions ranging from Digital Transformation programs utilizing the latest technologies from SAP and Oracle to a wide range of emerging Cloud based infrastructure, application and AI related solutions.
At Baer we aim to provide a best-in-class engagement experience for our consultants. Our job requirements are carefully vetted and are typically associated with pivotal programs offering tremendous opportunities to expand your skills leveraging the latest solutions.
Baer is an equal opportunity employer including disability/veteran.
