Senior RAG Engineer — Remote AI Retrieval Architect

Newcode.ai; Dublin; On-site; EUR 90,000 - 130,000; Full time

Job summary

Newcode.ai is a fast-growing legal tech and agentic AI company, operating remotely across the EU. You will own the retrieval pipeline end to end, including document parsing, embedding, indexing, and reranking, ensuring accuracy and latency targets are met.

The role emphasizes building dependable services in Python with FastAPI, focusing on production-grade retrieval, multi-step agentic loops, and data security. Collaboration with cross-functional teams is expected.

Qualifications

• 5+ years building backend systems in production.
• Experience shipping retrieval or RAG systems with real users.
• Experience running a vector index in production.
• Strong Python and FastAPI skills.
• Experience with PostgreSQL/Redis under load.
• Ability to own end-to-end maintenance and debt.
• Familiarity with OCR-heavy document ingestion and retrieval pipelines.

Responsibilities

• Own retrieval pipeline end to end: parsing, chunking, embeddings, indexing, and background reindexing.
• Design search combining semantic and keyword retrieval; fuse rankings and metadata filters.
• Build agentic retrieval with query decomposition and multi-step loops.
• Develop evaluation layers: golden sets, metrics, tracing for failures.
• Ship reliability-focused services in Python/FastAPI with background jobs.
• Ensure data security and strict tenant isolation across clients.
• Support multilingual retrieval and regional considerations.

Skills

Python

FastAPI

Qdrant

Embedding models

PostgreSQL

Redis

OCR ingestion

Information retrieval

Tools

FastAPI

PostgreSQL

Redis

Job description

Newcode.ai is a fast-growing legal tech and agentic AI company, operating remotely across the EU. You will own the retrieval pipeline end to end, including document parsing, embedding, indexing, and reranking, ensuring accuracy and latency targets are met.

The role emphasizes building dependable services in Python with FastAPI, focusing on production-grade retrieval, multi-step agentic loops, and data security. Collaboration with cross-functional teams is expected.