ML Engineer

We seek a highly skilled ML Engineer with 3-5 years of industry experience specializing in AI/ML, MLOps, Azure cloud computing, and Python to collaborate with our team of Data Scientists, Data Engineers, and Subject Matter Experts (SMEs).

Candidate should have strong expertise in traditional ML to design, develop, and deploy industrial AI solutions for refinery and petrochemical operations. The role focuses on time-series modeling, forecasting, optimization, and real-time deployment of ML systems that deliver measurable business impact (e.g., energy savings, yield improvement, process optimization).

The candidate will develop, implement, and deploy advanced AI-driven solutions, including traditional ML, deep learning, neural networks, and advanced analytics tailored specifically to the refining and petrochemical industry.

What You'll Be Doing

Design, build and deploy end-to-end AI/ML pipelines for industrial use cases at scale on cloud-based platforms or on-prem server

Select and implement appropriate AI/ML algorithms, and tools

Build and maintain data pipelines using Python & SQL for reliable data flow between IT/OT systems

Develop time-series forecasting and prediction models for process variables (e.g., temperature, pressure, yield, emissions, energy consumption)

Build optimization models for refinery & petrochemical operations (e.g., fuel optimization, throughput maximization, energy efficiency)

Work with high-frequency process data from historians (e.g., PHD, OPC, SCADA systems)

Perform feature engineering on multivariate time-series data, including lag features, rolling statistics, and domain-driven transformations

Train, evaluate, monitor, retrain and maintain AI/ML models

Deploy models into production using APIs, batch pipelines, or real-time streaming systems

Implement model monitoring, drift detection, and retraining pipelines

Collaborate with process engineers, SMEs, operations teams, and business users to translate domain problems into ML solutions

Ensure scalability, reliability, and performance of deployed AI systems

Regularly update and leverage industry trends and advancements in AI, ML, and Optimization technologies.

What We are looking for

3-5 years of experience in AI/ML engineering roles

Bachelors or Masters in Engineering, Computer Science, or equivalent experience

Strong programming skills in Python, R, or a similar language

Robust understanding of machine learning and deep learning methodologies, including training, inferencing, and performance monitoring

Strong experience in time-series modeling, forecasting, and prediction problems

Proven experience in industrial/process data (Oil & Gas / Manufacturing preferred)

Solid expertise with machine learning libraries (Numpy, Pandas, Matplotlib, Scikit-learn, Scipy, Seaborn, NLTK, Flask, Django) and frameworks (TensorFlow, PyTorch, Langchain, Langgraph).

Strong expertise in SQL for data extraction, transformation, and pipeline building

Understanding of feature engineering for time-series data

Experience in building end-to-end ML systems (data → model → deployment → monitoring_>retraining)

Hands-on experience with model deployment

Solid understanding of MLOps concepts:

Model versioning

CI/CD pipelines

Monitoring & alerting

Automated retraining

Experience handling large-scale data using PySpark / Apache Spark (good to have)

Strong analytical and problem-solving capability in industrial contexts

Ability to work closely with cross-functional teams (operations + data + IT)

Clear written and oral communication skills with a strong desire to share knowledge with business users, partners, and co-workers

Good to Have (Not Mandatory)

Exposure to Azure (Azure ML, Data Factory, Databricks, etc.)

Experience with real-time data streaming (Kafka, MQTT, OPC integration)

Exposure to GenAI / LLMs / Agentic systems (secondary skill, not core requirement)

Knowledge of refinery / petrochemical processes (CDU, FCC, Cracker, Boilers, etc.)