Lead Machine Learning Engineer

₹20,00,000 - ₹50,00,000 a year

The ideal candidate will own multiple production ML models for threat detection and ensure their performance, reliability, and scalability across environments while mentoring engineers and driving technical excellence.

 

1. Technical Leadership & Architecture

Design and own the ML architecture for threat detection platforms

Define model development standards, deployment patterns, and quality benchmarks

Make informed decisions on model selection, trade-offs, scalability, and cost

Conduct code and model reviews to ensure enterprise-level reliability and maintainability

Mentor ML engineers and contribute to capability building within the team

2. Model Development & Lifecycle Ownership

Design, develop, and deploy multiple production ML models, including:

Phishing detection

SMS scam detection

Call fraud detection

Keyword and behavioral anomaly detection

Own the end-to-end ML lifecycle:

Data ingestion and preprocessing

Feature engineering and training

Evaluation and validation

Deployment and monitoring

Apply advanced techniques such as ensemble learning, deep learning, and transfer learning

Optimize models for accuracy, latency, scalability, and operational efficiency

Manage model drift, retraining pipelines, and version control

 

3. ML Infrastructure & Deployment

Build and maintain production-grade ML pipelines

Develop and deploy model serving APIs using FastAPI or Flask

Containerize applications using Docker and Kubernetes

Implement CI/CD pipelines for ML workflows

Collaborate with backend, platform, and cloud infrastructure teams for seamless system integration

4. Monitoring, Observability & Explainability

Design and implement model monitoring, performance tracking, and alerting

Use monitoring tools such as Prometheus and Grafana

Implement logging and observability using ELK Stack or Splunk

Ensure model explainability and transparency using SHAP and LIME

Support audits, reviews, and operational diagnostics

5. Data Engineering & Workflow Orchestration

Design and manage data pipelines and workflows

Use Airflow, Prefect, or Dagster for orchestration

Perform large-scale data processing using SQL and Apache Spark

Integrate real-time and streaming systems using Kafka or RabbitMQ

Expert proficiency in Python

Strong experience with:

scikit-learn, XGBoost, LightGBM

TensorFlow and PyTorch

Hugging Face, spaCy, NLTK

Pandas, NumPy, Matplotlib, Seaborn

Optuna or scikit-optimize

Production experience with AWS, GCP, or Azure

(SageMaker, Vertex AI, or Azure ML)

Docker and Kubernetes

REST API development using FastAPI or Flask

CI/CD tools: GitHub Actions or GitLab CI

Databases: PostgreSQL and MongoDB

MLflow and/or Weights & Biases

Git and DVC for model and data versioning

Jupyter Notebook / JupyterHub

Pytest for testing and validation

Monitoring & Observability

Prometheus, Grafana

DataDog, New Relic, or equivalent APM tools

ELK Stack or Splunk

5–7+ years of experience in Machine Learning / Data Science

Proven track record of deploying ML models into production

Experience working in enterprise or large-scale systems

Prior experience leading or mentoring ML engineers

Strong understanding of software engineering best practices