Skip to content

Pranav Sharma

Senior AI Engineer | Forecasting, Pricing Analytics, and Decision Intelligence
Heilbronn, Germany
Phone: +49-15163776610 · Email: pranav.systems@proton.me · LinkedIn: linkedin.com/in/topranav

I design production-oriented ML systems that convert uncertainty into clear, testable decisions—across demand forecasting, pricing analytics, and risk-aware decision support.

Selected outcomes: ~100 person-hours/month forecasting effort reduction potential during scaled rollout, ~40 hours/month pricing analysis automation, quantile + conformal uncertainty validation, and Kubernetes-aligned deployment support.

Open Forecasting Sandbox · Open Pricing Decision Lite · Open Decision Kernel Lite · Resume · Blog · Contact

Profile

Senior AI Engineer focused on operationalizing machine learning in enterprise settings—from baselines and model development to reproducible evaluation, deployable artifacts, and decision-grade integration. Hands-on experience with rolling backtesting/benchmarking, probabilistic forecasting (quantiles), conformal evaluation, and production deployment support in Kubernetes environments. Strong record of mentoring junior engineers and students while translating ML work into structured, teachable workflows.

Professional Experience

Senior AI Engineer — ebm-papst, Heilbronn

03/2024 – Present

Demand Forecasting (Baselines → ML → Probabilistic)

  • Built end-to-end demand forecasting workflows for replenishment and safety-stock planning using statistical baselines, ML models, and probabilistic outputs.
  • Standardized evaluation across methods and horizons using MAE + |Bias| with rolling backtesting and baseline control layers.
  • Implemented quantile forecasting and validated calibration quality, including conformal evaluation of coverage versus interval width.
  • Benchmarked foundation-model approaches against classical and ML baselines with structured hyperparameter tuning and model comparison.
  • Estimated reduction of manual forecasting effort by ~100 person-hours/month as phased global rollout scales.

B2B Pricing Recommendation & Optimization

  • Delivered ML-based pricing recommendations for negotiation start prices to improve consistency and decision quality in sales workflows.
  • Automated pricing analysis workflows, reducing manual effort by ~40 hours/month.
  • Built demand/response models and optimization logic under explicit business guardrails, validated via offline backtesting.
  • Enabled interpretable driver analysis and what-if sensitivity support for stakeholder decision-making.
  • Supported deployment in Kubernetes environments and reproducible artifact workflows.

Research Associate — Hahn-Schickard, Villingen-Schwenningen

08/2018 – 02/2025

  • Achieved 91% classification accuracy in hyperspectral skin lesion analysis using transfer learning; contributed to follow-on research funding of €1.5M+.
  • Led development of deep-learning multi-class classifiers for hyperspectral data in collaboration with research partners.
  • Designed a reinforcement learning agent to improve Kubernetes cluster throughput and operational efficiency.
  • Implemented AI methods including K-means, federated learning, and explainable AI for imaging and silicon wafer analysis.
  • Managed resources to enable a cost-neutral 6-month project extension despite price increases.
  • Supervised and mentored 3 Master’s students.

Assistant Systems Engineer — Tata Consultancy Services (TCS), Noida, India

10/2013 – 04/2015

  • Resolved 3–5 maintenance tickets within a billing operations application environment (Sears account context).
  • Developed frontend components in Qt/C++ and extended backend functionality in SQL.
  • Contributed to stable production support through structured issue diagnosis and resolution.

Education

M.Sc. Mechatronics Engineering — Hochschule Ravensburg-Weingarten

10/2015 – 03/2018 · Grade: 1.8 (Germany)

  • Relevant coursework: Artificial Intelligence, Robot Learning, Robotics
  • Master’s thesis: Automatic Maneuver Selection Using Reinforcement Learning (IAV GmbH), Grade: 1.2
  • Internship: Automated Markov-based decision making (IAV GmbH)

B.Tech. Electronics and Instrumentation Engineering — SRM University

07/2009 – 06/2013 · Grade: 7.136 (India)

  • Relevant coursework: Artificial Intelligence & Expert Systems, Industrial Automation, Engineering Economics & Management
  • Internship: Attitude Determination and Control Subsystems (SRM Nanosatellite Lab)

Publications

  • Srivastava, A., Sharma, P., Sikora, A., Bittner, A., Dehé, A.
    Data-driven Modelling of an Indirect Photoacoustic Carbon dioxide Sensor (IEEE APSCON, 2024).
    DOI: 10.1109/APSCON60364.2024.10465802

  • Srivastava, A., Sharma, P., Sikora, A., Bittner, A., Dehé, A.
    Temporal Behavior Analysis for the Impact of Combined Temperature and Humidity Variations on a Photoacoustic CO₂ Sensor (IEEE APSCON, 2024).
    DOI: 10.1109/APSCON60364.2024.10465885

  • Sharma, P., Rüb, M., Gaida, D., Lutz, H., Sikora, A.
    Deep Learning in Resource and Data Constrained Edge Computing Systems (Machine Learning for Cyber Physical Systems).
    DOI: 10.1007/978-3-662-62746-4_5

Selected Projects

  • Forecasting Sandbox (Lite): transparent benchmarking and regime-aware model selection for time-series forecasting.
    → Open

  • Pricing Decision Lite: scenario-based pricing analytics under demand uncertainty with explicit decision rules.
    → Open

  • Decision Kernel Lite: structured decision analysis with Expected Loss, Minimax Regret, and CVaR.
    → Open

  • Mobile Autonomous Robot System (MARS) — Hochschule Ravensburg-Weingarten, Germany

  • SRMSAT (Nano-Satellite) — SRM University, India

Awards & Honors

  • Certificate of Commendation — SRM University & Indian Space Research Organization (ISRO)
  • Founder’s Scholar — SRM University

Certifications

  • Project Management Professional (PMP) — PMI
  • Generative AI Engineering with LLMs Specialization — IBM
  • Deep Learning Specialization — DeepLearning.AI
  • Computer Vision Expert Nanodegree — Udacity
  • Google Advanced Data Analytics Specialization — Google
  • AI Product Management Specialization — Duke University
  • Generative Adversarial Networks (GANs) — DeepLearning.AI

Skills

Programming

  • Python, SQL
  • Bash (basic), Git/GitHub

Python ML/Data Stack

  • NumPy, pandas, SciPy
  • scikit-learn
  • statsmodels
  • LightGBM
  • PyTorch
  • XGBoost
  • Matplotlib, Seaborn

Forecasting & Uncertainty Tooling

  • MAPIE (conformal prediction intervals)
  • Quantile modeling (e.g., LightGBM quantile objectives)
  • Backtesting frameworks (rolling-origin evaluation, custom pipelines)

MLOps & Deployment

  • Docker
  • Kubernetes (deployment support)
  • MLflow (if used)
  • DVC (if used)
  • Hugging Face (Spaces / model artifacts)
  • FastAPI / Streamlit (if used for apps)

Data & Platform

  • PostgreSQL / MySQL (if applicable)
  • Jupyter, VS Code
  • Linux/CLI workflows

Methods

  • Time-series forecasting (statistical + ML)
  • Probabilistic forecasting (quantiles, calibration checks)
  • Decision analysis (Expected Loss, Minimax Regret, CVaR)
  • Explainable AI / feature-level interpretability

Contact

For roles, technical collaboration, or consulting discussions:
Email: pranavsharma619@gmail.com
LinkedIn: linkedin.com/in/topranav

Compliance Note: This website contains independent portfolio and profile content only. Views are my own and do not represent any employer. No proprietary or confidential information is included.