Curriculum Vitae

Professional Summary

A results-driven Senior Python ML Engineer with over eight years of experience architecting and deploying high-impact AI and machine learning solutions. With a PhD in Python-focused statistical modeling and a proven track record of productionizing ML models in high-performance computing environments, I possess a unique blend of deep analytical expertise and hands-on software engineering skills. I excel in collaborating with scientists and researchers from complex domains to engineer robust and scalable machine learning models.

Key Strengths: Production ML deployment • Bayesian inference • RAG + LLM Agents (LangGraph) • Python (8+ years) • MLOps & Cloud • Physics-informed ML

Table of Contents

Professional Experience

Machine Learning & Analytics Engineer

Nomad Atomics, Australia | Sep 2024 - Present

Leading the development and deployment of multiple client-focused machine learning software in Python. Designed and executed all computational workflows within a Linux-native environment, deploying parallelized Python code on AWS.

Geophysical Survey Platform:

  • Architected and built anomaly detection and characterization software using geophysical survey data
  • Developed and containerized a production-grade data ingestion and processing pipeline using FastAPI and Docker, implementing Pydantic for strict, schema-based validation
  • Developed innovative anomaly detection algorithms leveraging signal processing, ML, and probabilistic modelling

Scientific Computing Framework (JAX):

  • Architected optimized ML software for solving million-parameter constrained optimization problems
  • Integrated physics-informed machine learning for 96% accurate feature characterization
  • Achieved 95% reduction in computation time leveraging JAX and GPU processing

Agentic AI Platform (LangGraph):

  • Built full-stack, AI-powered document generation application with LangGraph stateful agents
  • Deployed as Docker containerized, secure, multi-user service with FastAPI backend
  • Increased internal workflow productivity by estimated 5x

Quantum Sensor Analytics:

  • Built quantum-sensor data analysis package with innovative denoising algorithms
  • Achieved 90% reduction in inferred parameter uncertainty

Senior Machine Learning Research Fellow

Monash University, Melbourne, Australia | May 2022 – Aug 2024

Developed ML solutions for transport industry clients delivering $60M+ cost savings and 20% asset design efficiency.

Key Achievements:

  • Architected and deployed large-scale probabilistic simulation pipeline using parallelized Python on SLURM-managed Linux HPC cluster
  • Developed and deployed containerized interactive ML apps on AWS for training government professionals
  • Led end-to-end data lifecycle for major asset instrumentation project, from physical sensor installation to Python-based analytics platform
  • Developed full-stack Python FOSS for rare event forecasting, deployed on AWS for industry professionals

Machine Learning Research Associate

I.I.T. Bombay, India | Sep 2021 – Feb 2022

Developed predictive maintenance Python-based ML models for major Oil & Gas clients.

Key Achievements:

  • Delivered predictive maintenance model to forecast corrosion initiation in critical steel assets
  • Engineered Bayesian regression model achieving 90% accuracy in predicting remaining service life using sparse historical sensor data

Machine Learning Research Officer

Monash University, Melbourne, Australia | Feb 2019 – Feb 2020

Primary responsibility was developing ML solutions for multi-million-dollar transport industry projects.

Key Achievements:

  • Built complete data analytics pipeline in Python to process, clean, and analyze sensor data for VicRoads
  • Engineered core simulation engine using Bayesian statistical methods, informing high-stakes investment decisions leading to $800K savings
  • Managed end-to-end data lifecycle from physical sensor instrumentation to final performance analytics

Doctoral Researcher in Machine Learning

Monash University, Australia | Jan 2016 – Sep 2021

Developed novel AI algorithms in Python for rare event forecasting focused on construction and transport industry.

Key Achievements:

  • Delivered data-driven probabilistic assessment for Queensland Rail enabling $60 million in maintenance cost savings
  • Architected large-scale simulation pipeline using parallelized Python on SLURM-managed HPC cluster, executing millions of analyses
  • Engineered ML strategies that accelerated Bayesian simulations by over 99%, enabling previously infeasible large-scale sensitivity analyses
  • Published 15+ peer-reviewed articles in high-impact journals

Computational Mechanics Researcher

Ecole Centrale de Nantes, France | Sep 2014 – Jul 2015

Developed probabilistic algorithms for EGIS Industries, Paris.

Key Achievements:

  • Developed novel probabilistic algorithm to capture spatial variabilities in concrete specimens
  • Achieved 95% accuracy with physics-integrated probabilistic ML algorithms

Education

Doctor of Philosophy (PhD), Engineering

Monash University, Clayton Australia | 2022

Dissertation: Value of Information Framework for Structural Health Monitoring Under Uncertainty

  • Developed novel mathematical framework combining Bayesian decision theory, econometrics, and reliability analysis
  • Pioneered computational methods for large-scale uncertainty propagation
  • Recognized as first VoI framework of its kind in India and Australia

Master of Technology (MTech), Engineering

National Institute of Technology Warangal, India | 2015

Focus: Structural reliability, finite element analysis, probabilistic methods

Bachelor of Engineering (BE), Civil Engineering

Rajiv Gandhi Technological University, India | 2012

Focus: Structural engineering, mechanics, engineering mathematics

Technical Skills

Machine Learning & AI

  • Anomaly detection, supervised & unsupervised learning
  • Gaussian Processes, time series models
  • Bayesian Inference (MCMC), optimization, and forecasting
  • RAG + LLM Agent Development (LangGraph, LangChain)
  • Development of automation tools

Languages & Core Libraries

  • Python (Advanced, 8+ years): NumPy, SciPy, Pandas, PyMC, Matplotlib, Pytest, PyTorch, JAX, TensorFlow, Scikit-learn, Scikit-image
  • SQL, Bash
  • API documentation & MkDocs

MLOps & Cloud

  • Cloud Native Environments: AWS, HPC servers, GCP
  • Logging & Monitoring: Loguru, MLFlow
  • Docker & Containerization
  • CI/CD Pipelines using GitHub Actions
  • Linux (Ubuntu/Debian), SLURM (Workload Management)
  • Parallel & GPU-accelerated Computing in Python

Python Backend & Data Engineering

  • API Development (FastAPI, REST API)
  • Data Validation & Serialization (Pydantic)
  • Database Management (SQLite, SQL)
  • ETL/Data Pipelines
  • CLI Tool development
  • Configuration Management (TOML, Pydantic)
  • ASGI Servers (Uvicorn, Gunicorn)
  • Git, GitHub

Statistics & Uncertainty Quantification

  • Rare event forecasting, uncertainty quantification
  • Monte Carlo Simulation and MCMC
  • Extreme value modelling, optimization
  • Inverse problems, system state identification
  • Sensitivity analytics, surrogate modelling
  • Design of experiments

Data Visualization

  • Matplotlib, Plotly, Dash, ipywidgets, Streamlit
  • Geospatial mapping using QGIS and MapBox APIs
  • PowerBI & Tableau

Domain Expertise

  • Physics Informed Machine Learning
  • Infrastructure performance standards
  • Built solutions for: Construction & Transport, Water, and Mining Industry
  • Sensor data analytics: fusion, noise characterization, strain gauges, accelerometers
  • Structural Engineering

Professional & Leadership

  • Cross-functional team collaboration with SMEs
  • Client-facing communication
  • Technical writing & documentation
  • FOSS contribution & community engagement

Key Achievements & Impact

Production ML & Engineering

  • 95% computation reduction: JAX/GPU optimization for million-parameter ML problems (Nomad Atomics)
  • 96% feature accuracy: Physics-informed ML for geophysical characterization
  • 90% uncertainty reduction: Quantum sensor data analysis algorithms
  • 5x productivity gain: LangGraph-powered AI document generation system

Financial Impact

  • $60M cost savings: Queensland Rail maintenance optimization via ML-powered predictive analytics
  • 20% asset optimization: LXRP bridge asset reduction through probabilistic design
  • $800K per use case: VoI framework enabling multi-million-dollar VicRoads project justification
  • 99% efficiency gain: ML strategies accelerating Bayesian simulations

Operational Excellence

  • 90% prediction accuracy: ML corrosion model for Oil & Gas inspection optimization
  • Scaled automated Python solutions on HPC clusters, executing millions of analyses
  • Containerized ML apps on AWS for government training programs

Academic Excellence

  • 15+ publications: Peer-reviewed articles in high-impact ML and reliability journals
  • Multiple international conference presentations (ICOSSAR, ASCE)
  • Erasmus Mundus Scholarship by European Union

Open Source Contributions

PySTRA (Python Structural Reliability Analysis)

Core Developer | 2022 - Present

  • Developed & programmed advanced statistical algorithms for rare event forecasting
  • Contributed 3,500+ lines of code implementing reliability algorithms
  • Achieved 92% test coverage and established CI/CD pipeline via GitHub Actions

OSDAG (Open Steel Design and Graphics)

Mentor & Workshop Organizer | 2015 - 2021

  • Mentored a team of 3 graduates for core backend development
  • Conducted multiple hands-on training workshops for civil engineering academics and practicing engineers
  • Organized OSDAG pre-launch workshop in 2016
  • Developed video tutorials

Scholastic Achievements

  • Multiple peer-reviewed international scientific publications on machine learning and Bayesian statistics
  • Erasmus Mundus HERITAGE Scholarship by European Union (2014)
  • Post Graduate Student Scholarship by All India Council of Technical Education (A.I.C.T.E.), India (2013)

Publications

View my full publication list and citations on Google Scholar.

Professional Activities

Peer Review

  • Regular reviewer for high-impact journals in structural engineering and reliability
  • Contribute to scientific quality and integrity of published research

Community Engagement

  • Conference Session Chair: Organized technical sessions at regional symposia
  • Workshop Organization: Led OSDAG pre-launch workshop (2016)
  • Open Source Mentorship: Guide new contributors to PySTRA and OSDAG projects

Languages

  • English: Professional working proficiency
  • Hindi: Native proficiency
  • Bengali: Native proficiency

Professional Interests

Currently seeking ML/DS roles where I can apply my unique blend of theoretical rigor and production experience. Particularly interested in:

  • Production ML Systems: Building and deploying models that make real-time decisions at scale
  • Causal Machine Learning: Moving beyond correlation to understand interventions and counterfactuals
  • MLOps & Infrastructure: Robust pipelines for model development, deployment, and monitoring
  • Domain-Focused ML: FinTech, HealthTech, Climate Tech, Infrastructure Analytics
  • High-Stakes Decision-Making: Environments where model accuracy and interpretability have significant consequences

Contact

For contact details and ways to reach me, visit my Contact page.

For a narrative version of my background and transition to ML/DS, see my About page. For detailed project case studies, visit my Projects portfolio.