Job Summary
Years of Experience: 5-10years,
Work timing - 01:30 -10:30 PM
Preferable: Production Engineering knowledge Oil & Gas industry
Timeseries ML and constrained optimization for production ramp/sequence planning; ability to encode facility guardrails and drawdown targets.
Pressuresystem feature engineering using DHP/WHP/Manifold/Up/Downstream signals; comfort reconciling telemetry with physical intuition.
OT/historian (PI) data wrangling at scale; robust handling of gaps, sensor drift, and event slicing for ramp windows.
Azure ML model packaging, endpoints, monitoring; handson with CI/CD for retrains and can migrate from HPCtrained models to cloudserved artifacts.
Operatorcentric delivery: translating model outputs into clear ramp steps/visual cues (stoplights, countdowns) and validating against controlroom practice.
Key Responsibilities
A highly skilled Machine Learning Engineer with 5–10 years of experience in timeseries forecasting, sensorlevel feature engineering, and optimization models for industrial/energy systems. Strong background working with PI historian, operational telemetry, and production facility constraints. Proficient in designing endtoend ML pipelines—from OT data extraction and feature engineering to model deployment, monitoring, and operatorcentric UI delivery. Adept at translating complex ML/optimization outputs into clear operational instructions used by field/production teams.
Senior ML Engineer (6+ years)
Applied Scientist – Energy Optimization
OT Data + ML Specialist
Azure ML: Pipelines, endpoints, environments, registries
ADF and Azure Databricks (PySpark, Delta Lake, DLT)
CI/CD via Azure DevOps — YAML pipelines, automated retrains
Monitoring: Application Insights, Azure Monitor, data drift monitors
Containerization (Docker), ONNX model packaging
Working knowledge of containerization (Docker) and API deployment (FastAPI/Flask).
Skill Requirements
Experience in oil & gas, energy, or industrial automation environments.
Exposure to artificial lift systems (ESP/gaslift) or hydraulic flow models.
Knowledge of physicsbased modeling, surrogate modeling, or hybrid ML+physics workflows.
Experience with realtime streaming (Event Hubs, Kafka, IoT Hub).
Shape
Software Engineering Skills
Python (NumPy, Pandas, PyTorch, Scikitlearn)
PySpark, Delta Lake, ADLS
REST APIs (FastAPI/Flask)
Git, testing frameworks, logging & monitoring best practices
Shape
🔹 Soft Skills
Strong crossfunctional communication with production engineers, operators, SMEs
High ownership & ability to simplify complex ML outputs
Can work with ambiguity and evolving requirements
Comfortable leading design discussions and technical decisions