Job Description
Ovii's Interpretation of the Role
We need an experienced ML Engineer to build physics‑informed neural networks and end‑to‑end MLOps pipelines for real‑time simulation and digital‑twin workloads. The role owns the full lifecycle from feature engineering to model deployment, monitoring, and continuous improvement.
Role Snapshot
- ML Engineer (senior level)
- On‑site in Hyderabad, India
- Full‑time, individual contributor
- 7+ years of ML engineering experience
- Masters or PhD in CS, ML, Physics, or related field
Must-Have Requirements
- PyTorch
- TensorFlow
- Python
- NumPy
- SciPy
- pandas
- Databricks ML
- MLflow
- Unity Catalog
- Delta Lake
- Feature Store
- Docker
- Kubernetes/OpenShift
- Neural ODE solvers (torchdiffeq, diffrax)
- Physics‑Informed Neural Networks (PINNs)
- ML engineering
- applied ML
- scientific computing
- Master's or PhD
- On‑site work in Hyderabad, India
Nice-to-Have Signals
- GPU‑accelerated training
- Differentiable programming
- Discrete event simulation integration
- Domain exposure (Manufacturing, Logistics, Transportation)
Work Setup
- Location: Hyderabad, India
- Work mode: ONSITE
- Employment type: Full-Time
Not Specified in JD
- Salary range
- Visa sponsorship
- Remote eligibility
- Equity
- Bonus
- Travel requirement
What You'll Likely Work On
- Design and implement Physics‑Informed Neural Networks with domain constraints
- Develop neural ODE solvers and surrogate models for physics simulations
- Create hybrid ML architectures that blend data‑driven learning with physics‑based priors
- Optimize models for accuracy, inference speed, and resource efficiency
- Build scalable feature‑engineering pipelines on Databricks using PySpark
- Manage features in a Feature Store and construct Delta Lake training pipelines
- Orchestrate end‑to‑end ML pipelines with Databricks ML
- Track experiments, version models, and deploy via MLflow
- Implement model monitoring, drift detection, and alerting
- Establish CI/CD for ML pipelines and enforce governance with Unity Catalog
Good Fit If You Have
- Strong background in scientific or physics‑based ML applications
- Proven record of deploying production ML models at scale
- Experience with digital‑twin or simulation platforms is a plus
Skills
- ML frameworks (PyTorch, TensorFlow)
- Physics‑Informed Neural Networks (PINNs)
- Neural ODE solvers (torchdiffeq, diffrax)
- Python (NumPy, SciPy, pandas)
- Databricks ML & PySpark
- MLflow experiment tracking
- Unity Catalog governance
- Delta Lake feature storage
- Feature Store management
- Docker & Kubernetes/OpenShift
- Agile, cross‑functional teamwork