AI and Data Consultant

Murad Khalilov

I help teams bring AI and data projects into production.

Murad Khalilov

About me

Turning business challenges into practical AI solutions.

My background spans deep tech, retail, banking, and consulting. I work across model development, software engineering, and infrastructure.

I work with product, engineering, and domain teams to define requirements, build solutions, and support them through deployment and production use.

Experience
7+ years of experience
Location
Based in Düsseldorf

Previous roles at

  • Quantistry
  • ALDI DX
  • ING
  • EY

Services

AI Engineering

I build agentic AI systems and take them into production.

Monitoring & evaluationsTraces · metrics · quality checksUser inputQuestion · taskModel AModel BModel routingAgent runtimeResultTools & integrationsSearchAPIsDatabases& filesTask · cost · latencyAnswer · actionFunctions · MCP · CLI

  • Model serving and routing

    build infrastructure to serve AI models and route requests based on task requirements, cost, and latency

  • Agents and integrations

    develop single- and multi-agent workflows that access search, APIs, databases, and files through tools, MCP, and CLI integrations

  • Reliable execution

    implement failure handling, quality evaluations, and production monitoring

Data Science & MLOps

I develop machine learning models and build the systems to manage their full lifecycle.

TrainValidateDeployMonitorUser inputInferencePredictionsLearn · release · improve

  • Model development

    explore data, engineer features, and train and evaluate models

  • Reproducible pipelines

    build data processing, training, and inference pipelines with validation, experiment tracking, and model versioning

  • Lifecycle management

    deploy models, monitor performance and drift, and automate retraining with validation before release

Work experience

  1. Independent Consultant

    MKNX.DEV

    Dusseldorf, Germany

    10.2026 – present

  2. Senior AI/ML Engineer

    Quantistry

    Dusseldorf, Germany

    05.2025 – 03.2026

    Show details for Senior AI/ML Engineer at Quantistry
    • Led end-to-end delivery of ML/AI applications for the QuantistryLab simulation platform, from requirements definition and solution design to development, testing, deployment, and production support, coordinating efforts across back-end, DevOps, and ML teams
    • Designed and implemented a compound search system with an open-weights LLM, the Pydantic AI agent framework, and the Model Context Protocol (MCP), exposing it through FastAPI endpoints
    • Deployed and configured vLLM-based LLM serving on Kubernetes
    • Built CI/CD pipelines and Helm charts to automate deployments across staging and production environments
    • Instrumented the search system with OpenTelemetry spans and traces, integrating with the Honeycomb observability platform to monitor component-level latency and functional errors
    • Developed a custom evaluation dataset and implemented evaluations for retrieval relevance, answer correctness, tool-call accuracy, and end-to-end task success
    • Reduced infrared spectrum prediction time by 83% (from 60 to 10 minutes) by replacing a quantum-mechanical model with a pretrained graph neural network; fine-tuned the model using PyTorch, built and containerized the inference pipeline with Docker, and integrated it into the platform
    • Implemented an MLflow model registry with MinIO-backed artifact storage
    • Advised sales and science teams on ML/AI applications for prospective client projects, providing technical expertise to shape proposed solutions and prototypes
    • Technologies: AWS, Hetzner, Kubernetes, Helm, Docker, vLLM, Pydantic AI, MCP, Qwen, Llama 3, MLflow, MinIO, GitHub Actions, Python, FastAPI, OpenTelemetry, Honeycomb, PyTorch, Polars, pytest

  3. Senior Machine Learning Engineer

    ALDI DX

    Dusseldorf, Germany

    08.2023 – 04.2025

    Show details for Senior Machine Learning Engineer at ALDI DX
    • Designed and implemented training and inference pipelines for customer segmentation, customer lifetime value, and liquidity forecasting models on Databricks; orchestrated with Azure Data Factory
    • Developed custom data drift and model performance monitoring using statistical methods; introduced MLflow for experiment tracking, model versioning, and model registry management
    • Improved codebase quality and reduced the runtime of PySpark-based data pipelines by up to 50% through code refactoring, pipeline modularization, removal of redundant logic, and automated quality checks via CI/CD
    • Standardized development and release workflows by introducing GitFlow branching and a monthly release cycle
    • Technologies: Azure Databricks, Python, PySpark, Mlflow, SQL, Unity Catalog, Delta Lake, Azure Data Factory, Azure DevOps, GitLab CI/CD, pytest

  4. Data Scientist

    ING

    Frankfurt, Germany

    04.2020 – 07.2023

    Show details for Data Scientist at ING
    • Automated income and expense verification for loan applications by designing and deploying ML models on Google Cloud Platform (GCP), using PySpark for data processing, Airflow for orchestration, and Azure Pipelines for CI/CD, eliminating manual verification for up to 70% of applications
    • Developed Random Forest and XGBoost classifiers for transaction classification, app review classification, and KYC name screening, including data cleaning, feature engineering, and cross-validation
    • Addressed class imbalance through cost-sensitive training, oversampling/undersampling, and decision-threshold optimization to balance precision and recall
    • Collaborated with product owners, end-users, and engineering teams to gather requirements, design solutions, and deliver models, data visualizations, and interactive dashboards
    • Conducted workshops on building ML pipelines with Kedro and promoted its adoption across the department
    • Technologies: Python, PySpark, GCP, Airflow, BigQuery, Azure DevOps, scikit-learn, XGBoost, pandas, numpy, seaborn, Matplotlib, Dash, pytest

  5. Data Scientist

    EY

    Dusseldorf, Germany

    11.2018 – 03.2020

    Show details for Data Scientist at EY
    • Developed document analytics solutions using clustering, topic modeling, and text vectorization techniques
    • Designed and built interactive dashboards and data visualizations, including network graphs, to explore and communicate analytical findings
    • Collaborated with management and external clients to gather requirements, present findings, and iteratively refine solutions based on stakeholder feedback, contributing to securing two projects
    • Supported the adoption of software engineering best practices in a team of 3 data scientists, including version control, code reviews, and automated testing
    • Conducted ML workshops and presentations for students as part of employer branding and talent attraction initiatives
    • Technologies: Python, R, SQL, scikit-learn, spaCy, Doc2Vec, Shiny, ggplot2, Git

Portfolio

Selected projects coming soon

A selection of my work in machine learning, AI applications, and production infrastructure.

Contact

Have an AI or data project in mind?

Email me at or find me online: