- Location
- GDC Financial District, India
- Type
- Full-time
- Department
- Engineering
- Source
- Workday
Description
Techwave, we are always in an exercise to foster a culture of growth, and inclusivity. We ensure whoever is associated with the brand is being challenged at every step and is provided with all the necessary opportunities to excel in life. People are at the core of everything we do.
Who are we?
Techwave is a leading global IT and engineering services and solutions company revolutionizing digital transformations. We believe in enabling clients to maximize the potential and achieve a greater market with a wide array of technology services, including, but not limited to, Enterprise Resource Planning, Application Development, Analytics, Digital, and the Internet of things (IoT).
Founded in 2004, headquartered in Houston, TX, USA, Techwave leverages its expertise in Digital Transformation, Enterprise Applications, and Engineering Services to enable businesses accelerate their growth.
Plus, we're a team of dreamers and doers who are pushing the boundaries of what's possible.
And we want YOU to be a part of it.
Job Description
Key Responsibilities:
- Build root-cause ranking, incident classification and confidence-scoring models for Alarm Management.
- Prepare labelled datasets with engineers and convert operator feedback into training signals.
- Combine ML predictions with deterministic correlation and protection rules.
- Deploy and monitor models in SageMaker with versioning, rollback and champion-challenger evaluation.
- Provide explainable evidence and ensure low-confidence predictions remain subject to operator confirmation.
Technical skills required:
- Amazon SageMaker, Python, scikit-learn, XGBoost and model-serving APIs
- Supervised classification, anomaly detection, clustering such as HDBSCAN and confidence scoring
- Feature engineering using alarm sequences, topology, device attributes, weather and incident history
- Model evaluation using precision, recall, false-positive rate, calibration and operational acceptance
MLOps, model registry, deployment, monitoring, drift detection, retraining and explainability