Senior AI Engineer - Knowledge Graphs

About the role

You will own the design and implementation of knowledge graph systems that serve as the backbone for AI applications across global debt markets. You will translate ambiguous business requirements into precise graph structures that capture companies, legal entities, financial instruments, and their evolving relationships. You will lead the end-to-end development of graph-native pipelines that ingest, resolve, and serve complex financial knowledge at scale. You will mentor data scientists and engineers to adopt rigorous methods for entity resolution, relationship extraction, and graph-based retrieval. You will ensure that the knowledge infrastructure remains reproducible, observable, and aligned with strict financial and legal workflows. You will drive the adoption of state-of-the-art graph machine learning techniques to power discovery, risk analysis, and decision automation. You will act as a thought partner, pushing the frontier of how knowledge graphs create actionable intelligence across the 9fin platform.

Key facts

What you'll do

Design and architect scalable knowledge graphs that represent entities such as companies, sponsors, lenders, law firms, financial instruments, transactions, documents, events, and their intricate relationships.

Develop and maintain entity resolution and canonical data models that handle aliases, identity resolution, and record linkage across fragmented, noisy financial datasets.

Extract structured entities, events, and relationships from unstructured sources including filings, legal documents, news, transcripts, and research content using NLP and information extraction techniques.

Build graph-native search and retrieval systems that enable exploration of ownership structures, transaction histories, and connected entities with low latency and high accuracy.

Implement similarity, peer, and precedent discovery systems that leverage both graph structure and content signals to identify comparable companies, transactions, and scenarios.

Apply graph machine learning methods such as graph embeddings, node similarity, clustering, community detection, link prediction, and relationship scoring to derive predictive insights.

Develop and operate production data pipelines and entity stores that support scalable knowledge acquisition, curation, and serving at global market scale.

Write robust, production-ready Python code and collaborate closely with platform and infrastructure teams to integrate graph services into the broader 9fin ecosystem.

Work through the full model lifecycle, including experimentation, training, testing, monitoring, and deployment, with a strong focus on evaluation and data-centric practices.

Maintain a strong product orientation by deeply understanding end-user workflows and ensuring that graph-based solutions drive measurable efficiency and decision quality.

Leverage expertise in AWS AI infrastructure to optimize compute, storage, and networking for graph workloads in a secure and compliant manner.

Champion knowledge graph thinking across cross-functional teams, sharing techniques and elevating the organization's ability to build intelligent workflows.

Translate ambiguous business problems into well-defined, scoped technical bets in a fast-paced, startup-style environment where agility and ownership are essential.

Continuously learn and apply cutting-edge research in graph neural networks, retrieval-augmented generation, and related fields to maintain 9fin's technical edge.

Requirements

Demonstrate advanced expertise in knowledge graph design, ontology modelling, and semantic representation for complex financial domains.

Show strong experience with entity resolution, record linkage, alias handling, and entity disambiguation across heterogeneous and noisy data sources.

Prove ability to extract structured information from unstructured and semi-structured documents such as filings, legal contracts, transcripts, and research reports.

Have hands-on experience building graph-native search, retrieval, and exploration systems that expose deep relationship insights and connectivity patterns.

Exhibit a track record of designing similarity, peer discovery, and precedent analysis systems that combine graph topology with content-based matching.

Bring familiarity with graph machine learning techniques including embeddings, community detection, link prediction, and node classification in financial contexts.

Have experience delivering production-grade data platforms, entity stores, and graph pipelines that operate reliably at scale with strict performance and governance requirements.

Show strong proficiency in Python for building production-ready data products and integrating with distributed systems and cloud platforms.

Have experience managing the full model lifecycle, including experimentation, training, validation, testing, monitoring, and deployment in data-intensive environments.

Exhibit a strong product mindset, with the ability to translate user needs into robust technical solutions that directly improve decision-making and workflow outcomes.

Demonstrate good knowledge of AWS AI infrastructure, including compute, storage, and networking services relevant to graph and ML workloads.