Asra Anjum
Exceptional data scientist with experience turning raw data from multiple sources into valuable insights and creative solutions. Ability to translate vast amounts data into meaningful ndings that in uence business strategy. Solid background in computer science and analytics. Compelling presentation and reporting skills.
- Role
AI Engineer
- Years of Experience
3.4 years
Skillsets
- Transformers
- ML Pipelines
- MLOps
- Model deployment
- Model Validation
- Opensearch
- RAG systems
- S3
- Sagemaker
- semantic search
- Lambda
- vector embeddings
- Knn indexing
- XgBoost
- CI/CD
- LangChain
- Monitoring
- Predictive Modeling
- PySpark
- MLFlow
- Python - 1 Years
- SQL
- Docker
- ETL
- FastAPI
- Flask
- Generative AI
- LLMs
- Python - 1 Years
- NLP
- PyTorch
- Scikit-learn
- TensorFlow
- API Gateway
- AWS Bedrock
- Data preprocessing
- Feature Engineering
Professional Summary
3.4Years
- May, 2023 - Dec, 20252 yr 7 months
AI Engineer
eClinical Solutions LLC (R&D) - Aug, 2022 - Apr, 2023 8 months
Data Engineer(ETL)
eClinical Solutions LLC
Work History
3.4Years
AI Engineer
eClinical Solutions LLC (R&D)May, 2023 - Dec, 20252 yr 7 months
Designed and deployed enterprise-grade ML models for patient insights, anomaly detection, and workflow automation across large clinical datasets. Developed RAG-based clinical assistants using OpenAI embeddings + FAISS, improving clinical document search efficiency by 60–70%. Automated clinical data standardization and reconciliation pipelines, reducing manual effort by ~60%. Built end-to-end AI pipelines with Python, Scikit-Learn, TensorFlow, and PySpark for structured and unstructured clinical data. Deployed ML microservices using Flask + Docker and integrated models into enterprise business workflows, supporting production operations.
Data Engineer(ETL)
eClinical Solutions LLCAug, 2022 - Apr, 2023 8 months
Built production ETL pipelines for large clinical datasets using SQL & PySpark. Implemented automated data quality checks, transformations, and ingestion workflows for model-ready datasets. Contributed to data reconciliation automation projects, ensuring consistent and validated datasets for ML models.
Major Projects
2Projects
Automation of Clinical/External Data Reconciliation
Built rule-driven PySpark reconciliation engine using DAGs and SQL logic, reducing data mismatches and saving 20+ hours/week in manual effort.
Data Mapping Automation
Automated clinical data mapping (CDISC SDTM) using ML-based similarity detection and validation. Reduced manual effort by 70% with scalable pipelines and API integration.
Education
Bachelor Of Engineering (B.E) in Computer Science And Engineering
MVJ College Of Engineering (2022)