Semantic AI Engineer - Remote Work

At BairesDev®, we've been leading the way in technology projects for over 15 years. We deliver cutting-edge solutions to giants like Google and the most innovative startups in Silicon Valley.

Our diverse 4,000+ team, composed of the world's Top 1% of tech talent, works remotely on roles that drive significant impact worldwide.

When you apply for this position, you're taking the first step in a process that goes beyond the ordinary. We aim to align your passions and skills with our vacancies, setting you on a path to exceptional career development and success.

Semantic AI Engineer at BairesDev

In this role, you'll build the foundation of a neurosymbolic AI system designed to produce deterministic, trustworthy outputs. You'll design a bounded domain ontology and build the pipeline that turns heterogeneous data into a structured, typed graph, applying pragmatic modeling judgment along the way. This is your opportunity to work at the frontier of neurosymbolic AI, where classical data science meets rigorous ontology design to build AI systems that reason with real formal guarantees.

What You'll Do:

- Design a bounded domain ontology from a reference dataset, including entity types, typed relationships, cardinality, and shape rules.

- Build entity resolution and semantic alignment pipelines, mapping model-generated concepts to canonical ontology entities.

- Implement formal constraint reasoning for satisfiability, contradiction detection, and counterexample generation.

- Build SPARQL and RDF store operations behind an encapsulated semantic API.

- Design evaluation and reproducibility engineering, including accuracy metrics, ontology coverage, and reproducibility guarantees.

What we are looking for:

- 8+ years of experience in data science, ontology engineering, or semantic modeling.

- Strong, production-grade proficiency in Python for pipeline and engineering-grade code, not notebook analysis.

- Proven experience with ontology and semantic data modeling using RDF 1.1, OWL 2, and SHACL.

- Experience with entity resolution and semantic alignment, normalizing heterogeneous data into a typed symbolic graph.

- Background in formal constraint reasoning, including SMT solving concepts such as Z3.

- Experience with SPARQL and RDF store operations, such as Oxigraph or Apache Jena/Fuseki.

- Experience with evaluation and reproducibility engineering, including deterministic, reproducible pipeline results.

- Advanced proficiency in English.

Nice to have:

- Experience with NLP and embeddings, including entity extraction and disambiguation.

- Familiarity with LLM integration for hypothesis generation.

- Background in knowledge graph engineering at production scale.

- Formal methods, logic programming, or knowledge representation background, including Prolog, Datalog, ASP, or SMT solvers beyond Z3.

- Experience with data pipeline engineering and deterministic preprocessing.

- Experience with explainability and provenance system design.

- Familiarity with Langfuse and OpenTelemetry.

How we do make your work (and your life) easier:

- 100% remote work (from anywhere).

- Excellent compensation in USD or your local currency if preferred

- Hardware and software setup for you to work from home.

- Flexible hours: create your own schedule.

- Paid parental leaves, vacations, and holidays.

- Innovative and multicultural work environment: collaborate and learn from the global Top 1% of talent.

- Supportive environment with mentorship, promotions, skill development, and diverse growth opportunities.

Apply now and become part of a global team where your unique talents can truly thrive!