Semantic Backend Engineer Remote

INFUSE is committed to complying with applicable data privacy and security laws and regulations. For more information, please see our Privacy Policy.

We’re looking for an applied ML engineer to own the semantic ingestion pipeline, from raw PDFs to tagged, summarized, and embedded assets.

• Review application against job requirements.
• Video interview with hiring manager, followed by a test or short project.
• In‑person (or Zoom) interview with hiring team.
• Offer discussion if both parties are excited.

• Own the ETL pipeline from raw PDFs (S3-ingested) to structured resources.
• Finalize summarization and classification workflow using open‑source models with GPT‑4o fallback.
• Apply filtering logic (≤3 years old, ≤100 pages, etc.) to enforce resource quality.
• Map each asset to specific topic taxonomy (10+ per topic across ~9,000 topics).
• Generate dense embeddings using sentence‑transformers.
• Load and query embeddings with Milvus or pgvector.
• Implement freshness logic to index only new or updated content based on file diff, crawl timestamp, or hash.
• Build QA/evaluation harness: format compliance, recall@5, drift monitoring.
• Expose /v1/semantic-search via FastAPI with filtering and rank fusion.
• Collaborate closely with Tech Lead on UX integration and snippet generation.

• Python, PyTorch, sentence‑transformers, OpenAI APIs or similar pretrained LLMs.
• FastAPI, Milvus or pgvector, PyPDF/Tika, Airflow or Lambda for orchestration.
• Docker, GPU scheduling, Athena/Redshift SQL.

• Built ML pipelines that touched real users, not just notebooks.
• Worked on semantic search, embeddings, or large-scale tagging.
• Dealt with unstructured data and love turning chaos into clarity.
• Enjoy working fast, iterating with feedback, and tracking metrics that matter.

Your models decide what gets found, how it’s tagged, and which content and companies stand out. You’ll help define “relevance” and “freshness” for over a million resources and 50,000+ company pages—and make sure INKHUB stays ahead of the curve.

Seniority level:
Mid‑Senior level

Employment type:

Full‑time

Job function:
Construction, Software Development, and IT Services and IT Consulting

Referrals increase your chances of interviewing at INFUSE by 2×.

Poland: $–$