Lead AI/ML Engineer

Ideal candidate: Sagemaker + time series forecasting. If not then must be V Strong in one of them - Sagemaker OR time series forecasting, with moderate in other
We need someone with hands on experience in building forecasting models using deep learning/ML techniques such SARIMA, DeepAR, Prophet etc.
Also a good knowledge of MLOps especially using MLFlow will be needed. The team will deploy the solution on Databricks as well so knowledge of Databricks will be useful but not as crucial as others.
 
Role Summary
As a Lead AI/ML Engineer you are an experienced individual contributor who independently drives one or more AI/ML workstreams end-to-end. You own delivery outcomes for your assigned workstream, make key technical decisions, and interface directly with customer technical leads and stakeholders. You bring deep expertise in ML Ops and time-series forecasting to architect and implement scalable solutions on AWS.
 
Key Responsibilities
Design, develop, and deploy machine learning models for latent capacity prediction across pipeline systems (weather, gas turbine HP, compressor flow, line pack, equipment performance)
Build and maintain ML Ops infrastructure on AWS SageMaker including model registry, versioning, CI/CD pipelines, and multi-environment endpoints (Dev, Pre-Prod, Prod)
Conduct exploratory data analysis and feature engineering for time-series forecasting of pipeline operational data (SCADA, performance curves, hydraulic models)
Develop ensemble model strategies combining LSTM, Prophet, and XGBoost for improved prediction accuracy of latent capacity
Build automated model deployment workflows, training/evaluation pipelines, and retraining frameworks
Design real-time and batch inference architectures with API Gateway integration and model monitoring
Collaborate with data engineering team on feature stores and data pipeline integration from Bronze/Silver/Gold data lakehouse layers
Support hydraulic model integration with Gregg Engineering NextGen software for automated scenario generation
Independently own delivery of assigned ML workstream, driving technical decisions and ensuring quality
Mentor L4/L5 team members on ML best practices, code reviews, and architectural patterns
Interface directly with customer technical leads to align on requirements, review progress, and resolve technical blockers
 
Required Skills & Qualifications
Strong experience with AWS SageMaker, including SageMaker Pipelines, Model Registry, and Feature Store
Proficiency in time-series forecasting (LSTM, Prophet, XGBoost, ensemble methods)
Experience with ML Ops practices: CI/CD for ML, model monitoring, automated retraining
Python (NumPy, Pandas, scikit-learn, TensorFlow/PyTorch)
Experience with real-time and batch inference architectures
Knowledge of data lakehouse architectures (S3, Glue, Redshift)
Understanding of industrial/operational data (SCADA, IoT sensors) is a plus
Experience in Energy & Utilities domain preferred
Demonstrated ability to independently lead technical workstreams and make architectural decisions
Experience mentoring junior engineers or consultants
Strong communication skills for customer-facing interactions