Senior ML Engineer (Knowledge Graphs)
About Osavul
Osavul is a product company building an AI-driven intelligence platform that helps governments, international organisations, enterprises and NGOs detect and counter hybrid threats. We're a fast-growing team on a mission that matters.
Role Overview
We're looking for a Senior ML Engineer to join our engineering team and help develop the AI capabilities behind our intelligence products, with a particular focus on NLP, information extraction, and knowledge graphs.
Our platform processes large volumes of data from multiple sources, including text, social media, imagery, and geospatial data. One of our key challenges is identifying entities and relationships across these sources and connecting relevant information so analysts can understand how actors, events and narratives relate across sources, locations, and time.
In this role, you'll work with traditional ML/NLP approaches and modern language models, contribute to the development of our knowledge graph architecture, and integrate models into production data pipelines. You'll be involved in technical decisions, from selecting and evaluating models to getting them into production.
We're looking for someone with a solid ML background who is equally comfortable writing production code. This is a hands-on engineering position focused on building and maintaining production systems, not a research role.
What matters most: production ML/NLP experience, hands-on information extraction, and experience designing and building knowledge graphs.
Requirements
Engineering Skills
- Strong Python skills and proven experience developing and maintaining AI/ML services in production.
- Experience with FastAPI, Docker, and asynchronous programming.
- Good understanding of databases, including PostgreSQL, Elasticsearch, and vector databases.
- Experience integrating ML models into distributed data pipelines using tools such as Celery, RabbitMQ, Apache Kafka, or similar technologies.
- Solid software engineering practices, including writing maintainable code, testing, debugging, and supporting production systems.
AI Skills
- 3+ years of hands-on experience in ML/NLP engineering, including deploying models to production and supporting them after release.
- Practical experience with information extraction from unstructured data, including entity extraction, relation extraction, entity resolution, or entity linking.
- Experience designing and building knowledge graphs, including ontology and graph schema design, and working with graph databases such as Neo4j. Experience with GraphRAG is also relevant.
- Good understanding of traditional NLP approaches, transformer architectures, and the application of language models to information extraction tasks.
- Experience with deep learning frameworks such as PyTorch.
- Experience evaluating ML/NLP models and measuring their performance.
- Upper-intermediate (B2) English or higher.
Nice to Have
- Hands-on experience with fine-tuning and/or self-hosted deployment of open models, including approaches such as LoRA/PEFT and SFT, model serving with vLLM or similar tools, and inference optimisation techniques such as quantisation.
- Experience with multimodal models, computer vision, or geospatial data, including satellite imagery and remote sensing.
- Background in threat intelligence, OSINT, geospatial intelligence, or defence.
We Offer
- Opportunity to contribute to a mission-driven product used by governments, international organisations, enterprises and NGOs to tackle global security challenges.
- Real ownership in shaping our knowledge graph direction, and the freedom to drive experiments and bring your ideas to production.
- Remote-first: work from Ukraine or anywhere in Europe.
- Unlimited paid time off, plus company-wide holidays.
- Software and AI tools you need for your work are covered.
- Annual budget for conferences, courses and professional development.
Hiring Process
- Recruiter interview
- ML interview
- Engineering interview
- Final interview with leadership
- Reference check and offer