Required Skills

- Python Test Automation

- ML Testing &
- Validation

- CI/CD &

- MLOps

- Data Pipeline Testing

- API &

- Microservices Testing

- Cloud Platforms

- SQL &

- Databases

Nice to Have

- MLflow / ML Platforms

- Data Quality Tools

- Performance Testing

- Docker &
- Kubernetes

Designation | Lead, Automation Test Engineer Qualification | B.E or B.Tech Experience (in years) | 6 | We are seeking a Lead Software Engineer – Machine Learning Testing with 6–8 years of experience in software quality engineering, including hands-on validation of data-driven and machine learning applications. The ideal candidate combines robust Python-based test automation skills with practical knowledge of data quality, model evaluation, ML pipelines, and production monitoring.

Key Responsibilities Machine Learning Validation &

- Verification • Design and execute end-to-end V&V; strategies for classical ML use cases, including regression, classification, clustering, forecasting, and anomaly detection.
- Define risk-based test plans, test scenarios, test cases, acceptance criteria, and traceability across the ML lifecycle.
- Validate training, validation, and test datasets for completeness, accuracy, consistency, representativeness, leakage, imbalance, and schema quality.
- Evaluate model performance using business-appropriate and technical metrics such as precision, recall, F1-score, ROC-AUC, MAE, RMSE, MAPE/SMAPE, and calibration.
- Perform robustness, boundary, negative, bias, explainability, reproducibility, and non-regression testing.
- Validate model behavior across segments, edge cases, unseen data, and changing operating conditions.
- Ensure V&V; coverage from data preparation and experimentation through deployment, monitoring, retraining, and retirement. Test Automation &
- ML Pipeline Quality • Build scalable Python and PyTest-based automation frameworks for data, model, API, batch, and end-to-end testing.
- Automate checks for data pipelines, feature engineering, model artifacts, inference services, and integration points.




- Integrate automated quality gates into CI/CD and ML-Ops pipelines.
- Develop test suites for APIs, microservices, scheduled pipelines, and cloud-based ML workloads.
- Perform sanity, functional, integration, regression, performance, resilience, and user acceptance testing across QA, UAT, and production-like environments.
- Create reusable test utilities, synthetic test datasets, mocks, fixtures, and baseline comparisons. ML Monitoring &
- Production Quality • Define and validate monitoring for model quality, data drift, concept drift, prediction distribution, latency, throughput, failures, and service availability.
- Verify alert thresholds, dashboards, logging, lineage, model versioning, and rollback readiness.
- Analyze production issues and quality signals to support root-cause analysis, corrective actions, and continuous improvement.
- Collaborate with Data Scientists, ML Engineers, Software Engineers, Product Managers, and Governance teams to define release readiness and quality evidence.

Quality

Assurance &

- Reporting • Analyze test results, identify quality risks, and communicate actionable insights to engineering and business stakeholders.
- Log, prioritize, and track defects using standard defect-management tools.
- Maintain high-quality documentation for test strategies, test evidence, validation reports, model cards, and release recommendations.
- Contribute to test standards, review practices, and continuous improvement of AI/ML quality engineering.

Required Skills &

Experience • 6–8 years of experience in software testing and test automation, with practical exposure to AI/ML or data-intensive applications.





- Strong programming expertise in Python and hands-on experience with PyTest or equivalent test frameworks.
- Good understanding of supervised and unsupervised machine learning concepts, model lifecycle, feature engineering, and statistical validation.
- Hands-on knowledge of model evaluation metrics for classification, regression, forecasting, and imbalanced datasets.
- Experience testing data pipelines, APIs, microservices, databases, and batch-processing workflows.
- Experience with Git-based workflows and CI/CD pipelines.
- Working knowledge of ML-Ops concepts such as model registry, experiment tracking, deployment, monitoring, drift, and retraining.
- Knowledge of Azure, AWS, Databricks, or equivalent cloud/data platforms.
- Familiarity with SQL and relational or NoSQL databases.
- Strong verbal and written communication skills, with experience working across multi-stakeholder and onshore–offshore delivery models.
- Qualification: B.E./B.Tech or an equivalent degree in Computer Science, Engineering, Data Science, or a related discipline. Preferred / Nice-to-Have • Experience with MLflow, Azure Machine Learning, Amazon SageMaker, Databricks, or similar ML platforms.
- Exposure to data-quality and validation tools such as Great Expectations, Pandera, or equivalent frameworks.
- Knowledge of responsible AI testing, including fairness, explainability, transparency, privacy, and governance controls.
- Experience with performance testing tools such as JMeter, k6, or Locust for inference APIs and ML services.
- Familiarity with Docker, Kubernetes, observability platforms, and production support for ML workloads.
- Exposure to GenAI or agentic AI testing is an added advantage but is not the primary focus of this role. Soft Skills • Analytical and critical thinking • Curiosity and continuous learning • Strong debugging and problem-solving mindset • Strategic communication, active listening, and translation of technical quality risks into business impact • Collaboration, ownership, and attention to detail

📌 Lead Automation Test Engineer - Machine Learning - M L (Bengaluru)
🏢 Cigres Technologies
📍 Bengaluru