Applied Machine Learning Engineer

thinkproject
15 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Working hours
Regular working hours
Languages
English
Experience level
Intermediate

Job location

Tech stack

A/B testing
Agile Methodologies
Artificial Intelligence
Airflow
Google BigQuery
Computer Programming
Continuous Integration
Information Engineering
Document Management Systems
Data Flow Control
Python
Machine Learning
Named Entity Recognition
Raw Data
TensorFlow
SQL Databases
Systems Integration
Management of Software Versions
Google Cloud Platform
Feature Engineering
PyTorch
Model Validation
Keras
GIT
Scikit Learn
Information Technology
Machine Learning Operations
Front End Software Development
Software Version Control
Apache Beam
Unsupervised Learning

Job description

We are seeking a hands-on Applied Machine Learning Engineer to join our team and lead the development of ML-driven insights from historical data in our contracts management, assets management and common data platform. This individual will work closely with our data engineering and product teams to design, develop, and deploy scalable machine learning models that can parse, learn from, and generate value from both structured and unstructured contract data., * Model Development: Design and implement machine learning models using structured and unstructured historical contract data to support intelligent document search, clause classification, metadata extraction, and contract risk scoring.

  • BigQuery ML Integration: Build, train, and deploy ML models directly within BigQuery using SQL and/or Python, leveraging native GCP tools (e.g., Vertex AI, Dataflow, Pub/Sub).
  • Data Preprocessing & Feature Engineering: Clean, enrich, and transform raw data (e.g., legal clauses, metadata, audit trails) into model-ready features using scalable and efficient pipelines.
  • Model Evaluation & Experimentation: Conduct experiments, model validation, A/B testing, and iterate based on precision, recall, F1-score, RMSE, etc.
  • Deployment & Monitoring: Operationalize models in production environments with monitoring, retraining pipelines, and CI/CD best practices for ML (MLOps).
  • Collaboration: Work cross-functionally with data engineers, product managers, legal domain experts, and frontend teams to align ML solutions with product needs.

Requirements

You will use BigQuery and its ML capabilities (including SQL and Python integrations) to prototype and productionize models across a variety of NLP and predictive analytics use cases. Your work will be critical in enhancing our platform's intelligence layer, including search, classification, recommendations, and risk detection., * Education: Bachelor's or Master's degree in Computer Science, Machine Learning, Data Science, or a related field.

  • Total Experience 4+ years with 3+ Years of ML Expertise and Strong applied knowledge of supervised and unsupervised learning, classification, regression, clustering, feature engineering, and model evaluation.

  • NLP Experience: Hands-on experience working with textual data, especially in NLP use cases like entity extraction, classification, and summarization.

  • GCP & BigQuery: Proficiency with Google Cloud Platform, especially BigQuery and BigQuery ML; comfort querying large-scale datasets and integrating with external ML tooling.

  • Programming: Proficient in Python and SQL; familiarity with libraries such as Scikit-learn, TensorFlow, PyTorch, Keras.

  • MLOps Knowledge: Experience with model deployment, monitoring, versioning, and ML CI/CD best practices.

  • Data Engineering Alignment: Comfortable working with data pipelines and tools like Apache Beam, Dataflow, Cloud Composer, and pub/sub systems.

  • Version Control: Strong Git skills and experience collaborating in Agile teams. Preferred Qualifications:

  • Experience working with contractual or legal text datasets.

  • Familiarity with document management systems, annotation tools, or enterprise collaboration platforms.

  • Exposure to Vertex AI, LangChain, RAG-based retrieval, or embedding models for Gen AI use cases.

  • Comfortable working in a fast-paced, iterative environment with changing priorities.

Benefits & conditions

By combining information management expertise and in-depth knowledge of the building, infrastructure, and energy industries, Thinkproject empowers customers to efficiently deliver, operate, regenerate, and dispose of their built assets across their entire lifecycle through a Connected Data Ecosystem.

About the company

thinkproject was founded in 2000 in Munich, Germany. Since then, the company has grown into the leading provider for cross-enterprise collaboration and information management in Europe.

Global customers from the construction and engineering industries are served from thinkproject’s home base in Munich and via a range of subsidiaries across Europe.

thinkproject addresses today’s digitization challenges in construction and engineering by providing state-of-the-art software solutions as well as industry expert consulting and services.

Apply for this position