Senior Ontology Engineer (Python)
Andersen is hiring a Senior Ontology Engineer for a project building a large-scale Knowledge Graph and delivering AI-powered data and identity solutions.
andersen · На сервисе с: 03.10.26 15:01
Зарплата не указанаПольшаНидерландыПортугалияPorto
Andersen is hiring a Senior Ontology Engineer for a project building a large-scale Knowledge Graph and delivering AI-powered data and identity solutions.
The company is a global technology provider delivering data analytics and AI-powered solutions that help organizations better understand customer behavior, optimize marketing performance, and make informed business decisions. By transforming large volumes of data into actionable insights, it enables enterprises to improve audience engagement, measure the effectiveness of their initiatives, and enhance decision-making. The company works with a diverse range of customers, supporting them in navigating an increasingly data-driven and rapidly evolving digital landscape.
The project is focused on building a large-scale Knowledge Graph and Identity platform that models relationships between audiences, content, brands, devices, and behavioral data. It combines graph technologies, big data processing, and AI-powered enrichment to support identity resolution, audience intelligence, measurement, and advanced analytics.
- Owning the end-to-end design, development, and versioning of core RDF/RDFS/OWL ontologies and SHACL validation frameworks.
- Defining ontology standards, derived-attribute schemas, aggregation/scoring logic, and governance practices aligned with W3C and relevant industry standards.
- Leading ontology design reviews and translating business requirements into scalable knowledge graphs and semantic data models.
- Co-designing derivation and transformation pipelines with Data Engineering using Databricks/Spark, including schemas and validation checkpoints.
- Building scalable, production-grade knowledge graph pipelines using Python and SPARQL, including entity resolution, record linkage, and data enrichment.
- Defining graph vs. data lake strategies to balance query performance, storage, scalability, and refresh costs.
- Applying embeddings and LLM-based approaches to ontology mapping, entity disambiguation, semantic similarity, and GraphRAG use cases.
- Collaborating with Data Engineering, Data Science, Platform, and Product teams to ensure production-ready graph solutions.
- Mentoring Ontology Engineers and junior specialists and leading technical workshops on ontologies, knowledge graphs, and semantic technologies.
- Bachelor's degree in Computer Science, Information Science, Computational Linguistics, Mathematics, or related fields.
- Hands-on experience in ontology engineering, semantic data modeling, or knowledge graph development for 5+ years, with a demonstrable track record of production ontologies at scale.
- Deep expertise in W3C semantic web standards: RDF, RDFS, OWL, SPARQL 1.1, and SHACL.
- Hands-on experience building and validating graph schemas in a production triplestore (Amazon Neptune, Stardog, GraphDB, Jena, or equivalent).
- Strong Python, including production-quality, well-tested code; comfortable building data pipelines and graph processing workflows.
- First-principles understanding of description logics, ontology design patterns, and the practical trade-offs between OWL expressivity and triplestore scalability.
- Hands-on experience with entity resolution, record linkage, or deduplication at scale (mapping messy, multi-source real-world data to clean ontological representations).
- Strong communication skills, ability to defend ontological modeling decisions in design reviews and explain trade-offs to non-specialist stakeholders.
- Level of English – from Intermediate+ and above.
- Master's degree or PhD in Computer Science, Information Science, Computational Linguistics, Mathematics, or related fields.
- Hands-on experience with Amazon Neptune or Stardog, including data virtualization (Neptune Orion or Stardog Virtual Graphs) over data lake sources.
- Experience designing aggregation and derivation logic that converts raw behavioral event data into durable, graph-resident derived attributes.
- Domain knowledge in media, entertainment, or ad tech (TV viewership (ACR/STB), digital audience modeling (device graphs, identity resolution), or ad exposure data).
- Familiarity with industry content and identity schemas: EIDR, Schema.org VideoObject, DDEX, or equivalent.
- Experience with embedding models, vector databases (Milvus, Pinecone, Weaviate), and GraphRAG architectures (LangChain/LlamaIndex).
- Familiarity with GNN-based approaches to knowledge graph reasoning or entity resolution.
- Working knowledge of PySpark and Databricks for large-scale transformation pipelines.
- Experience in teamwork with leaders in FinTech, Healthcare, Retail, Telecom, and others. Andersen cooperates with such businesses as Samsung, Siemens, Johnson & Johnson, BNP Paribas, Ryanair, Mercedes, TUI, Verivox, Allianz, T-Systems, etc..
- The opportunity to change the project and/or develop expertise in an interesting business domain.
- Guarantee of professional, financial, and career growth! The company has introduced systems of mentoring and adaptation for each new employee.
- The opportunity to earn up to an additional 1,000 EUR per month, depending on the level of expertise, which will be included in the annual bonus, by participating in the company's activities.
- Access to the corporate training portal, where the entire knowledge base of the company is collected and which is constantly updated.
- Bright corporate life (parties / pizza days / PlayStation / fruits / coffee / snacks / movies).
- Certification compensation (AWS, PMP, etc).
- Referral program.
- Private health insurance and sports compensation, depending on the type of employment.
Join us!
Похожие вакансии Data Science & ML
Сайты компаний
This is a modeling role with production responsibility, and it is close to a founding one. You will define how relevance is measured here, build the training data from scratch, and own the models that follow. The interesting constraint is that suggestions must return within tens of milliseconds of each keystroke, in cities where map data is thin and people type in mixed scripts, so model choice is an evidence-based trade-off you will own rather than a preference: gradient-boosted ranking on behavioral data today, transformers and large language models where they earn their place in query understanding and cross-script matching, and neural reranking if the failure analysis justifies it. Ground truth comes from what drivers, couriers and customers actually do, and from completed rides, so a large part of the craft is turning messy behavioral logs into labels you can trust. You will measure your impact through offline evaluation and online A/B tests, and changes reach millions of customers in weeks.
Зарплата не указанаГрузияТбилиси
About the role
Geo Search runs the search that tens of millions of customers use to say where they are going, across many countries where the commercial maps everyone else leans on are often wrong, incomplete, or simply missing. We are building our own search and recommendation stack, which means we own the data, the ranking, and the measurement. The team is cross-functional, spanning backend, machine learning, mobile, and QA, and works with a product manager focused on relevance and with geo analysts. It owns place search and autocomplete, geocoding, ranking and personalization, location detection and pickup selection, and its own search screens on Android and iOS. It is measured on order conversion, search conversion, and mean reciprocal rank
We are looking for a Senior Data Scientist to own ranking, relevance and recommendation for geo search: the models that decide which places a customer sees, in what order, and how that changes with context.
We are looking for a Senior Data Scientist to own ranking, relevance and recommendation for geo search: the models that decide which places a customer sees, in what order, and how that changes with context.
This is a modeling role with production responsibility, and it is close to a founding one. You will define how relevance is measured here, build the training data from scratch, and own the models that follow. The interesting constraint is that suggestions must return within tens of milliseconds of each keystroke, in cities where map data is thin and people type in mixed scripts, so model choice is an evidence-based trade-off you will own rather than a preference: gradient-boosted ranking on behavioral data today, transformers and large language models where they earn their place in query understanding and cross-script matching, and neural reranking if the failure analysis justifies it. Ground truth comes from what drivers, couriers and customers actually do, and from completed rides, so a large part of the craft is turning messy behavioral logs into labels you can trust. You will measure your impact through offline evaluation and online A/B tests, and changes reach millions of customers in weeks.
Responsibilities
- Own ranking, relevance and recommendation for geo search end to end, from training data through to models serving in production
- Build the label pipeline that turns search sessions and completed rides into trustworthy training data, including correction for position bias and other presentation effects
- Train and own the models that order results, and the confidence model that decides per query whether we serve our own answer or fall back to an external provider
- Build query understanding for our markets, including cross-script matching, using large language models to label offline and distilling into models fast enough for the keystroke path
- Own evaluation end to end: the offline replay harness that scores recorded sessions against real rides, the error analysis that turns failures into work for the right team, and the online experiments that prove impact
- Keep models healthy after launch as data and cities shift
Qualifications
Minimum qualifications
- 5 or more years building models that shipped and improved a production metric
- Direct experience with ranking, search relevance, or recommendation systems, including how they are evaluated
- Expert Python and SQL, fluency with gradient boosting, and working knowledge of transformers
- Experience taking a model to production and owning it afterwards
- The ability to work across teams, since search quality work generates data and engineering tasks that others own
Preferred qualifications - Depth in geocoding, autocomplete, or place search
- Learning to rank in practice: pairwise and listwise objectives, MRR, NDCG, Hit@k, and their failure modes
- Relevance tuning on OpenSearch or Elasticsearch, including analyzers
- Multilingual or cross-script search, for example Arabic and Arabizi or Urdu and Roman Urdu
- Distilling language models under a latency budget, and experience in mapping or geospatial products in developing markets
Benefits
- Help us challenge injustice by creating fair choices for millions of people across 47 countries.
- Develop your professional skills with access to mentoring, career consulting, and learning programs.
- Collaborate with teams around the world and gain international experience through our Global Talent Exchange Program.
- Engage in company-wide challenges, awards, sports activities, employee-led social impact and volunteering projects.
- Work alongside people who take initiative, speak openly, and challenge themselves to grow.
- Improve your language skills through co-financed courses and internal speaking clubs.
Final benefits may vary depending on the location.
hh.ru
Зарплата не указанаУзбекистанТашкентОфис
Обязанности:
-Разработка и внедрение моделей машинного обучения и глубокого обучения (ML/DL) для бизнес-задач.
-Оптимизация и поддержка существующих алгоритмов.
-Работа с большими данными: очистка, подготовка, анализ.
-Интеграция моделей в продакшн (API, микросервисы).
-Исследование новых подходов в области AI (LLM, генеративные модели).
Требования:
-Опыт работы от 2 лет в области ML/AI.
-Знание Python и библиотек: TensorFlow, PyTorch, scikit-learn.
-Опыт работы с SQL и NoSQL базами данных.
-Понимание архитектуры нейронных сетей, NLP, CV.
-Английский язык — уровень B2 и выше.
Будет плюсом:
-Опыт работы с облачными платформами (AWS, GCP, Azure).
-Знание MLOps и CI/CD.
-Участие в AI-хакатонах или open-source проектах.
HireSeeker собирает вакансии со всех площадок и присылает только релевантные. Бесплатно.