Company Description Axionix is a global leader in digital transformation, collaborating with top technology companies to drive meaningful innovation.

Guided by a purpose-driven approach, Axionix combines advanced technology and skilled talent to design and implement impactful solutions.

With a strong focus on agility and future-proof strategies, Axionix partners with clients throughout the entire lifecycle of their projects.

The company specializes in delivering top-quality digital solutions and building exceptional tech teams.

About the Role We are looking for a Machine Learning Engineer (3–5 years experience) with strong expertise in time-series modeling, MLOps, Python, and SQL to build and deploy industrial AI solutions for refinery and petrochemical operations.

You will work closely with Data Scientists, Data Engineers, and Process SMEs to convert high-frequency process data into real-time AI systems that deliver measurable business impact such as energy savings, yield improvement, throughput optimization, and emissions reduction .

This role is ideal for someone who enjoys working at the intersection of process engineering + machine learning + production deployment .

Responsibilities: Design, build, and deploy end-to-end AI/ML pipelines for industrial use cases at scale (cloud or on-prem) Develop time-series forecasting and prediction models for process variables (temperature, pressure, yield, energy, emissions) Build optimization models for refinery and petrochemical operations (fuel optimization, energy efficiency, throughput maximization) Engineer features from multivariate high-frequency time-series data (lag features, rolling stats, domain transforms) Build reliable data pipelines using Python & SQL connecting IT/OT systems (PHD, OPC, SCADA, historians) Deploy models via APIs, batch pipelines, or real-time streaming Implement model monitoring, drift detection, CI/CD, automated retraining Collaborate with process engineers and operations teams to translate domain problems into ML solutions Ensure scalability, reliability, and performance of deployed AI systems Qualifications: 3–5 years of experience in ML/AI engineering roles Strong Python programming and SQL expertise Proven experience in time-series forecasting and prediction Hands-on experience building end-to-end ML systems (data → model → deployment → monitoring → retraining) Solid understanding of MLOps (model versioning, CI/CD, monitoring, retraining) Experience with ML/DL libraries: Scikit-learn, Pandas, Num Py, Tensor Flow or Py Torch Strong feature engineering skills for time-series data Experience deploying models to production Excellent analytical and problem-solving skills in industrial contexts Strong fit (Preferred) Experience with industrial/process data (Oil & Gas / Manufacturing) Optimization techniques, Reinforcement Learning , or constrained optimization Experience with real-time data (Kafka, MQTT, OPC, historians) Py Spark / Apache Spark for large-scale data Exposure to Azure ecosystem (Azure ML, Data Factory, Databricks) Nice to have: Knowledge of refinery/petrochemical processes (CDU, FCC, Cracker, Boilers) Exposure to Gen AI / LLMs / Agentic systems (secondary skill) Ways to stand out: Demonstrated impact from industrial ML projects (cost savings, optimisation gains) Production-grade MLOps pipeline experience Strong coding and debugging skills Experience solving constrained optimisation problems in process industries