Autonomize - Senior Software Quality Assurance Engineer

Key Responsibilities :

- Design and execute test strategies for AI/ML systems across data, model, and deployment stages

- Validate datasets for quality, consistency, and completeness

- Test machine learning models for accuracy, performance, and robustness

- Identify bias, anomalies, and edge-case failures in model predictions

- Perform regression testing on retrained models

- Automate testing workflows and integrate with CI/CD pipelines

- Monitor model performance post-deployment (drift, degradation)

- Document test cases, results, and defects clearly

Required Qualifications :

- Bachelors/Masters degree in Computer Science, Data Science, or related field

- 2 to 5 years of experience in QA/testing with exposure to AI/ML systems

- Strong programming skills in Python or similar languages

- Understanding of machine learning concepts and evaluation metrics

- Experience with test automation tools and frameworks

Technical Skills :

- Python (pandas, NumPy, scikit-learn)

- Machine Learning basics (supervised/unsupervised learning)

- Model evaluation metrics (Accuracy, Precision, Recall, F1-score)

- API testing (Postman, REST APIs)

- SQL and data validation techniques

- Test automation (PyTest, Selenium or similar)

- CI/CD tools (Jenkins, GitHub Actions)

- Basic knowledge of MLOps tools (MLflow, Kubeflow)

Text Skills (Must-Have) :

- Strong written and verbal communication skills

- Ability to write clear, concise test cases and bug reports

- Good documentation skills for test plans and results

- Analytical thinking and problem-solving ability

- Attention to detail and critical thinking

- Collaboration and teamwork skills

- Ability to explain technical concepts to non-technical stakeholders

- Time management and task prioritization

- Curiosity and willingness to learn new technologies

Preferred Skills :

- Experience with NLP, Computer Vision, or Recommendation Systems

- Familiarity with cloud platforms (AWS, Azure, GCP)

- Knowledge of AI ethics, fairness, and bias testing

- Experience with performance and load testing tools

- KPIs / Success Metrics

- Model defect detection rate

- Test coverage across ML lifecycle

- Reduction in production issues

- Accuracy and reliability of validated models