Senior AI Platform Engineer

Description

The team maintains a core platform for entity management, governance, cross-references (XREFs), relationships and business context discovery.

Key skills include knowledge graphs, Neo4j, Elasticsearch, OpenSearch, entity resolution, NLP, NER, LLMs, Gemma, Llama, GLiNER, spaCy, PostgreSQL, Kubernetes, Datadog, AI-assisted development and data modeling.

Requires 7+ years of experience.

Posted 27-10-2026.

Responsibilities

• Grow the core platform covering entity management, governance, XREFs, relationships and business context discovery.
• Build and refine NER pipelines that combine LLMs, open-source NLP models, gazetteers, pattern matching and blacklists.
• Expand entity extraction to more content sources, including streaming and real-time feeds.
• Make search better through entity resolution, personalized search, metadata filters and relationship-based exploration.
• Design and keep up graph relationship models for traversal, visualization and business context mapping.
• Build access rules at the entity level for retrieval, search and exploration.
• Connect new data sources and link the platform to downstream applications and business systems.
• Turn business needs that are hard to define into scalable technical designs and AI-driven workflows.
• Use AI-assisted development tools, checking generated code, architecture choices and solutions critically.
• Work with stakeholders across several business areas to set priorities and shape the platform's direction.
• Onboard team members, mentor engineers and share knowledge.

Requirements

• 7+ years of software engineering experience, including designing and running data-intensive platforms in production.
• Strong hands-on skill with Elasticsearch and/or OpenSearch, information retrieval and entity resolution.
• Hands-on work with graph databases and knowledge graphs, including Neo4j and Cypher.
• Solid applied NLP and NER experience with Gemma, Llama, GLiNER, spaCy and LLM-based extraction.
• Working knowledge of PostgreSQL and Kubernetes, plus monitoring tools like Datadog.
• Proven record ingesting, syncing and managing data from multiple source systems.
• Systems-thinking mindset with strong architecture and data modeling skills.
• Skill in modeling intricate business areas and how they relate.
• Hands-on time with coding assistants like GitHub Copilot, Cursor, Claude and ChatGPT, plus agentic workflows.
• Skill at judging, testing and improving AI-generated output with sound engineering judgment.
• Track record of enforcing who can see what, including restricted-data filtering.
• Excellent verbal and written communication.
• Advanced English.
• Preferred: experience in Oil & Gas, Energy, Utilities, Mining or other asset-intensive industries.
• Preferred: exposure to large-scale enterprise data governance and master data management.
• Preferred: experience building enterprise search, discovery or knowledge management platforms.
• Preferred: familiarity with graph visualization and relationship analytics.
• Preferred: experience designing AI-powered search and retrieval systems.

Conditions

Remote, based in LATAM.

Work mode: remote.

Requisition reference 006fu00000eClH3AAK-2.

Hiring is based on skills and qualifications only, without regard to age, disability, religion, gender, sexual orientation, socioeconomic status or nationality.