Machine Learning Engineer

About Gradera — Digital Twin & Physical AI Platform 

At Gradera, we are building a next-generation Digital Twin and Physical AI platform that enables enterprises to model, simulate, and optimize complex real-world systems. Our work brings together strategy, architecture, data, simulation, and experience design to power decision-making across large-scale operational environments such as manufacturing, logistics, and supply chain networks. 

 

This platform-led initiative applies AI-native execution, advanced simulation, and governed orchestration to help organizations test scenarios, predict outcomes, and continuously improve performance. We operate with an enterprise-first mindset prioritizing reliability, transparency, and measurable business impact as we build intelligent systems that scale beyond a single industry or use case. 

Machine Learning (ML) Engineer 

Overview 

We are seeking skilled ML Engineers to join our Simulation & Scenario Enablement team. This is a specialized role at the intersection of machine learning engineering and physics-based simulation. You will design and implement production-grade ML pipelines, build physics-informed neural networks (PINNs) that respect physical constraints, and develop neural architectures that accelerate simulation workloads. You will own the full MLOps lifecycle — from feature engineering and model training to deployment, monitoring, and continuous improvement — ensuring ML models reliably power real-time scenario evaluation and digital twin intelligence. 

Our core ML engineering stack includes: 

ML Frameworks & Development 

• PyTorch and TensorFlow for neural network development 

• Physics-Informed Neural Networks (PINNs) for constraint-aware modeling 

• Neural ODE solvers (torchdiffeq, diffrax) for continuous-time dynamics 

• Python (NumPy, SciPy, pandas) for numerical computing 

MLOps & Platform 

• Databricks ML for scalable model training and pipelines 

• MLflow for experiment tracking, model registry, and deployment 

• Unity Catalog for ML asset governance and lineage 

• Delta Lake for feature storage and versioned training data 

• Feature Store for feature management and serving 

Production & Monitoring 

• Model serving and inference optimization 

• Model monitoring, drift detection, and alerting 

• CI/CD for ML pipelines 

• Containerized model deployment (Docker, Kubernetes/OpenShift) |
  
  

Key Responsibilities 

• Design and implement Physics-Informed Neural Networks (PINNs) with domain constraints 

• Develop neural ODE solvers and surrogate models for physics simulations 

• Build hybrid ML architectures combining data-driven learning with physics-based priors 

• Optimize neural models for accuracy, inference speed, and resource efficiency 

• Design scalable feature engineering pipelines using Databricks and PySpark 

• Manage features in Feature Store and build Delta Lake training pipelines 

• Build end-to-end ML pipelines on Databricks ML 

• Track experiments, version models, and deploy using MLflow 

• Implement model monitoring for drift, performance, and prediction quality 

• Build CI/CD for ML and ensure governance via Unity Catalog 
  
  

Preferred Qualifications 

• 7+ years of experience in ML engineering, applied ML, or scientific computing roles 

• Master’s or PhD in Computer Science, Machine Learning, Computational Science, Physics, or related field 

• Track record of deploying ML models in production at scale 

• Experience with physics-based or scientific ML applications 

• Experience working in agile, cross-functional teams 
  
  

Highly Desirable 

• Experience with ML for digital twin or simulation platforms 

• Background in computational physics, numerical methods, or scientific computing 

• Experience with differentiable programming and automatic differentiation frameworks 

• Familiarity with discrete event simulation or agent-based modeling integration 

• Experience with GPU-accelerated training and inference optimization 

• Publications or patents in physics-informed ML, neural ODEs, or surrogate modeling 

• Contributions to open-source ML/scientific computing projects 

• Exposure to industrial domains such as Manufacturing, Logistics, or Transportation is a plus 

 

Location: Hyderabad, Telangana 
Department: Engineering 
Employment Type: Full-Time