Graph RAG - Knowledge Engineer

Chryselys; Hyderabad, Chennai District; Hybrid; INR 1,800,000 - 2,400,000; Full time

Job summary

Chryselys in Hyderabad seeks a Graph RAG Knowledge Engineer to design, build and operate Python/FastAPI services for extracting entities and relationships from unstructured text. You will resolve entities, maintain the graph ontology, and serve graph-augmented retrieval with vector search for complex questions.

Responsibilities include building extraction services, entity resolution, graph schema design, and producing a unified retrieval context.

Qualifications

• 5–9 years software engineering with knowledge‑graph construction and applied NLP delivered to production.
• Has built a knowledge graph from unstructured text — not queried an existing one, and not a CRUD application on a graph database.
• Graph at production scale with millions of nodes and edges; incremental updates with stable identity; bounded depth/timeouts.
• Entity resolution at corpus scale with blocking and candidate generation and calibrated thresholds.
• Graph database in production: Neo4j, Amazon Neptune or equivalent; Cypher/openCypher fluency.
• Ontology and taxonomy modelling with schema evolution without breaking downstream consumers.
• Extraction: NER and relation extraction — LLM‑based, model‑based (spaCy, scispaCy, transformers) or hybrid.
• Graph vs. vector: knows where graph retrieval wins and that hybrid is production norm.

Responsibilities

• Build and maintain Python/FastAPI services to extract entities and relationships from unstructured documents.
• Perform entity resolution and candidate generation with scalable matching.
• Design and evolve graph schema and ontology; manage incremental ingest and provenance on edges.
• Fuse graph and vector results into a single, ranked, cited context for retrieval.
• Instrument, monitor and support production services.

Skills

Software engineering

Knowledge graphs

Applied NLP

Graph production scale

Entity resolution

Graph databases

Ontology modelling

NER & relation extraction

Python

FastAPI

Tools

Neo4j

Amazon Neptune

openCypher

spaCy

scispaCy

transformers

Python

FastAPI

Docker

pytest

Git

CI/CD

AWS

S3

ECS/EKS

Job description

Graph RAG - Knowledge Engineer

Design, build and operate the Python/FastAPI services that extract entities and relationships from unstructured documents, resolve them to canonical identifiers, maintain the knowledge graph, and serve graph-augmented retrieval alongside vector search for multi‑hop and relational questions.

Responsibilities

• Build entity and relation extraction services over unstructured documents molecules, brands, indications, therapeutic areas, endpoints, claims.
• Build entity resolution: alias handling, blocking and candidate generation, fuzzy and embedding matching, calibrated thresholds, human review routing.
• Design and maintain the graph schema and ontology; incremental ingest, node and edge deduplication and merging, provenance on every edge.
• Fuse graph and vector results into a single ranked, cited context for the retrieval service.
• Instrument, monitor and support the services in production.

Qualifications

• 5–9 years software engineering, with demonstrable knowledge‑graph construction and applied NLP delivered to production.
• Has built a knowledge graph from unstructured text — not queried an existing one, and not a CRUD application on a graph database.
• Graph at production scale. Millions of nodes and edges; incremental updates with stable node identity; supernode and traversal‑explosion handling with bounded depth and timeouts.
• Entity resolution at corpus scale. Blocking and candidate generation that avoid O(n) comparison, with measured precision on a labelled sample.
• Graph database in production. Neo4j, Amazon Neptune or equivalent; Cypher / openCypher fluency.
• Ontology and taxonomy modelling. Schema evolution without breaking downstream consumers; judgement on node vs. edge vs. property.
• Extraction. NER and relation extraction — LLM‑based, model‑based (spaCy, scispaCy, transformers) or hybrid, with the judgement to choose.
• Graph vs. vector judgement. Knows where graph retrieval wins — multi‑hop, relational, comparative and aggregate questions — and that hybrid is the production norm.
• Python and FastAPI in production. Python 3.11+, async, Pydantic, Docker, pytest, Git and CI; AWS as a consumer (S3, ECS/EKS, Bedrock, Neptune or self‑hosted Neo4j).

Preferred

Biomedical ontologies and registries: UMLS, MeSH, SNOMED, RxNorm, ICD-10, DrugBank, ChEMBL.

• Life sciences or pharma domain experience; RDF/SPARQL alongside property graphs.
• GraphRAG approaches: community detection for corpus‑level summarisation, local vs. global search.