Machine Learning Engineer

Role Overview

We are seeking a Python Machine Learning Engineer with 3–5 years of experience, specializing in building, training, and deploying classical and deep learning models. The ideal candidate should have strong expertise in data-driven modeling, statistical analysis, and domain-specific applications such as mass spectrometry data processing.

1. Core Machine Learning Development

• Design, develop, and optimize machine learning models using frameworks such as PyTorch, TensorFlow, and scikit-learn
• Apply supervised and unsupervised learning techniques for real-world problem-solving
• Strong understanding of:
• Machine Learning algorithms (Regression, Classification, Clustering)
• Model evaluation techniques (Cross-validation, ROC-AUC, Precision/Recall, F1-score)
• Hands-on experience with Deep Learning architectures:
• CNN (Convolutional Neural Networks)
• RNN / LSTM (Sequential data modeling)
• Perform feature engineering, feature selection, and data preprocessing for structured and unstructured datasets
• Experience handling large-scale datasets and improving model performance through tuning and optimization

2. Data Processing & Analysis

• Strong expertise in data manipulation and analysis using:
• Pandas
• NumPy
• Polars (optional)
• Ability to clean, transform, and prepare raw datasets for ML pipelines
• Experience with time-series or signal-based data is a plus

3. Advanced ML Techniques for Signal & Scientific Data

• Experience working with high-dimensional, noisy, and time-series datasets
• Strong understanding of:
• Signal processing techniques (smoothing, filtering, baseline correction)
• Feature extraction from sequential and waveform-like data
• Data normalization and scaling techniques for model stability
• Ability to apply machine learning for:
• Pattern detection and classification in complex datasets
• Noise reduction and signal enhancement using ML/DL models
• Predictive modeling for quantitative estimation and trend analysis
• Experience with:
• Peak/event detection and segmentation in time-series data
• Statistical modeling and curve fitting for calibration and prediction tasks
• Handling structured outputs derived from sensor/instrument data
• Familiarity with processing instrument-generated datasets (CSV, logs, time-series signals)

4. Model Deployment & Engineering (ML-focused)

• Develop scalable pipelines to serve ML models using FastAPI, Flask, or Django
• Experience in writing clean, modular, and production-ready Python code
• Use of Git for version control and collaboration
• Ability to write unit tests and ensure code quality

5. MLOps (ML Lifecycle Focus)

• Experience with:
• Model tracking and experimentation tools (MLflow, DVC)
• Monitoring model performance and handling model drift
• Containerization using Docker for ML workflows
• Understanding of CI/CD pipelines for ML model deployment (basic level sufficient)

6. Database & Data Handling

• Experience with databases such as:
• PostgreSQL / MySQL
• MongoDB / Redis (optional)
• Ability to efficiently store, query, and process large datasets
• Familiarity with data pipelines and ETL processes

Key Requirements Summary

• Strong foundation in Machine Learning & Deep Learning (non-LLM focused)
• Hands-on experience with scientific data, especially mass spectrometry
• Proficiency in Python and data processing libraries
• Experience in end-to-end ML pipeline development and deployment