{"id":1406370,"url":"https://alion.io/job/three-across-graph-rag-knowledge-engineer","title":"Graph RAG - Knowledge Engineer","company":{"id":3809846,"name":"Three Across","domain":"thethreeacross.com","url":"https://alion.io/company/three-across","size_band":null,"is_staffing_agency":true,"employer_type":"agency","is_intermediary":false,"listed_via":null,"ats_vendor":null,"truth_index":null},"role":"AI/ML","role_family":"AI/ML","seniority":"middle","employment_type":"full_time","work_mode":"on_site","remote_scope":null,"remote_scope_basis":null,"remote_working_hours":null,"hiring_geo_confidence":"structured","locations":["Hyderabad, India"],"countries":["IN"],"hiring_countries":[],"hiring_countries_total":0,"salary":null,"salary_estimate":{"min_usd":19500,"max_usd":48000,"period":"year","method":"role_seniority_country_remote_cell","sample_n":22},"experience_years_min":4,"visa_sponsorship":false,"relocation_package":false,"has_equity":false,"technologies":[{"name":"Amazon ECS","optional":false},{"name":"Amazon EKS","optional":false},{"name":"Amazon Neptune","optional":false},{"name":"Amazon S3","optional":false},{"name":"AWS","optional":false},{"name":"AWS Bedrock","optional":false},{"name":"Docker","optional":false},{"name":"FastAPI","optional":false},{"name":"Git","optional":false},{"name":"GraphRAG","optional":false},{"name":"Knowledge Graph","optional":false},{"name":"LLM","optional":false},{"name":"Neo4j","optional":false},{"name":"NER","optional":false},{"name":"NLP","optional":false},{"name":"Pydantic","optional":false},{"name":"Pytest","optional":false},{"name":"Python","optional":false},{"name":"RAG","optional":false},{"name":"spaCy","optional":false},{"name":"Kubernetes","optional":true}],"status":"live","first_seen_at":"2026-09-28T17:49:38Z","employer_posted_date":null,"last_verified_at":"2026-09-28T17:49:38Z","board_verified":false,"closed_at":null,"days_open":1,"trust":{"level":"not_scored","repost_count":null,"flags":[],"days_open":1},"description":"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.\n\nResponsibilities\n\nBuild entity and relation extraction services over unstructured documents molecules, brands, indications, therapeutic areas, endpoints, claims.\nBuild entity resolution: alias handling, blocking and candidate generation, fuzzy and embedding matching, calibrated thresholds, human review routing.\nDesign and maintain the graph schema and ontology; incremental ingest, node and edge deduplication and merging, provenance on every edge.\nFuse graph and vector results into a single ranked, cited context for the retrieval service.\nInstrument, monitor and support the services in production.\n\nQualifications\n\n4 9 years software engineering, with demonstrable knowledge-graph construction and applied NLP delivered to production.\nHas built a knowledge graph from unstructured text not queried an existing one, and not a CRUD application on a graph database.\nGraph at production scale. Millions of nodes and edges; incremental updates with stable node identity; supernode and traversal-explosion handling with bounded depth and timeouts.\nEntity resolution at corpus scale. Blocking and candidate generation that avoid O(n ) comparison, with measured precision on a labelled sample.\nGraph database in production. Neo4j, Amazon Neptune or equivalent; Cypher / openCypher fluency.\nOntology and taxonomy modelling. Schema evolution without breaking downstream consumers; judgement on node vs. edge vs. property.\nExtraction. NER and relation extraction LLM-based, model-based (spaCy, scispaCy, transformers) or hybrid, with the judgement to choose.\nGraph vs. vector judgement. Knows where graph retrieval wins multi-hop, relational, comparative and aggregate questions and that hybrid is the production norm.\nPython 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).\n\nPreferred\n\n Biomedical ontologies and registries: UMLS, MeSH, SNOMED, RxNorm, ICD-10, DrugBank, ChEMBL.\nLife sciences or pharma domain experience; RDF/SPARQL alongside property graphs.\nGraphRAG approaches: community detection for corpus-level summarisation, local vs. global search.\n\nKey Notes\n\nNOT A FIT FOR THIS ROLE\n\nGraph analytics data scientists without service-building experience graph-database developers whose work was application CRUD rather than knowledge-graph construction ontologists without production engineering general RAG engineers without entity-resolution depth.","description_format":"text","description_chars":2757,"description_truncated":false,"requirements":{"experience_years_min":4,"management_years_min":null,"team_size_min":null,"manages_managers":false,"education":null,"security_clearance":false,"languages":[]},"benefits":[],"hiring_locations":[],"hiring_excludes":[],"relocation_offered":false,"industries":["Biotechnology"],"lifecycle":[{"event":"open","at":"2026-09-28T18:00:02Z"}],"liveness":{"score":52,"band":"ok","label":"Likely open","p_open":1,"p_active":0.516,"p_room":1,"age_days":0,"expected_fill_days":17,"reasons":["seen:0","agency","win:early"],"computed_at":"2026-09-29T05:45:00Z"},"pay":null,"html_url":"https://alion.io/job/three-across-graph-rag-knowledge-engineer","json_url":"https://alion.io/job/three-across-graph-rag-knowledge-engineer.json","meta":{"generated_at":"2026-09-30T01:41:26Z","cache_seconds":300,"methodology":"https://alion.io/methodology","terms":"https://alion.io/terms","contact":"https://alion.io/contact","api":"https://alion.io/developers","usage":{"tier":"crawler","counted_by":"address","units_charged":1,"used_today":1279,"day_limit":5000,"remaining_today":3721,"minute_limit":60,"resets_at":"2026-10-01T00:00:00Z"}}}