Senior Software Engineer, Ontology & Reasoning Systems

Jobtailor; Connecticut; On-site; USD 120,000 - 155,000; Full time

Job summary

Jobtailor in the United States (Connecticut) is seeking a backend-focused engineer to own the ontology and rule layer that unifies enterprise data into a single, traceable reasoning model. You will model entities and constraints across diverse sources, deriving conclusions from facts, and build retrieval and validation pipelines to support complex workflows.

You will work with knowledge graphs and graph data, employ LLMs at ingestion, ensure provenance, and ship reliable production services and

Qualifications

• 5+ years of experience building backend systems in modern languages or equivalent practical experience.
• Strong formal and mathematical foundation, including discrete mathematics, logic, and graph theory.
• Ability to reason about soundness, completeness, and tractability, and to express complex domains as formal rules.
• Hands-on experience with declarative, logic-based, or rule-based reasoning systems (e.g., Datalog, Prolog, ASP, SMT).
• Practical experience building LLM-powered systems with structured extraction, RAG, or classification pipelines.
• Deep experience with knowledge graphs and graph data (RDF, SPARQL, property graphs; Neo4j).
• Experience designing systems whose outputs trace back to inputs (provenance, derivation chains).
• Strong debugging, testing, and validation practices.

Responsibilities

• Own the ontology and rule layer that unifies structured, semi-structured, and unstructured enterprise data into a single reasoning model.
• Model entities, relationships, events, and constraints across heterogeneous sources, and develop rules that derive conclusions from combinations of facts.
• Use LLMs at the ingestion boundary for extraction, normalization, and categorization, with appropriate validation of model-generated outputs.
• Make system findings traceable by connecting each conclusion to the source facts and rules that produced it.
• Build retrieval capabilities, including vector search, keyword search, and graph traversal, to support reasoning workflows.
• Improve quality through entity resolution, constraint modeling, and structured handling of conflicting or overlapping sources.
• Ship production services and research prototypes with a focus on correctness, reliability, and maintainability.

Skills

Backend systems

Discrete mathematics

Logic

Graph theory

Rule-based reasoning

LLM integration

Knowledge graphs

Provenance

Debugging

Tools

Datalog

Answer Set Programming

Prolog

SMT solvers

Neo4j

SPARQL

RDF

Job description

Responsibilities

• Own the ontology and rule layer that unifies structured, semi-structured, and unstructured enterprise data into a single reasoning model.
• Model entities, relationships, events, and constraints across heterogeneous sources, and develop rules that derive conclusions from combinations of facts.
• Use LLMs at the ingestion boundary for extraction, normalization, and categorization, with appropriate validation of model-generated outputs.
• Make system findings traceable by connecting each conclusion to the source facts and rules that produced it.
• Build retrieval capabilities, including vector search, keyword search, and graph traversal, to support reasoning workflows.
• Improve quality through entity resolution, constraint modeling, and structured handling of conflicting or overlapping sources.
• Ship production services and research prototypes with a focus on correctness, reliability, and maintainability.

Requirements

• 5+ years of experience building backend systems in a modern language such as Python, Go, Java, Scala, Rust, or similar, or equivalent practical experience.
• A strong formal and mathematical foundation, including discrete mathematics, logic, and graph theory.
• The ability to reason about soundness, completeness, and tractability, and to express complex domains as formal rules and constraints.
• Hands‑on experience with declarative, logic‑based, or rule‑based reasoning systems such as Datalog, Answer Set Programming, constraint logic programming, Prolog, production rule engines, SMT solvers, or similar.
• Practical experience building LLM‑powered systems, including structured extraction, RAG, or classification pipelines, with sound judgment about where model outputs require validation.
• Deep experience with knowledge graphs and graph data, including RDF, SPARQL, property graphs, or graph databases such as Neo4j.
• Experience designing systems whose outputs trace back to their inputs, including provenance, derivation chains, or evidence trails.
• Strong debugging, testing, and validation practices, with attention to correctness.