Senior RAG Engineer

Newcode.ai; United States; Remote; USD 101,000 - 146,000; Full time

Job summary

Newcode.ai is seeking a Senior Backend Engineer to own retrieval and embedding pipelines across confidential document sets. You will influence architecture early and ensure accuracy of citations in model outputs.

You’ll build retrieval components in Python with FastAPI, assess vector DB performance, and maintain production-grade services with strong data isolation. Remote across the EU/EEA.

Qualifications

• At least five years building backend systems that run in production.
• Two+ years shipping retrieval or RAG systems used by real users.
• You have run a vector index in production with memory and latency trade-offs.

Responsibilities

• Own retrieval pipeline end to end: parsing, chunking, embeddings, indexing, and maintenance.
• Design search combining semantic and keyword retrieval, including reranking.
• Build agentic retrieval with query decomposition and multi-step loops.
• Create evaluation layers with golden sets and robust metrics.

Skills

Python

FastAPI

Vector databases (Qdrant)

Embedding models

PostgreSQL/SQL

OCR-heavy document ingestion

Tools

Qdrant

Job description

About Newcode.ai

Newcode.ai is a fast-growing legal tech and agentic AI company transforming how legal work is done. With teams across Norway, Sweden, Ireland, the US and growing we work at the intersection of law, technology, and intelligence. We move fast, think big, and take pride in doing things the right way.

Note: We believe in being transparent about what it’s like to work at Newcode. As a fast-growing startup, we’re building and evolving every day. That means not every process, playbook, or framework is already in place, and priorities can shift quickly.

The people who thrive here are comfortable with ambiguity, take ownership, and don’t wait for perfect direction. They are resourceful, proactive, and able to “figure it out”—solving problems, creating structure where needed, and helping build the company as they go. If you are good with this then, great! Keep reading to learn more.

The role

You’ll own retrieval. When someone asks our product a question, something has to find the right passage across large sets of confidential documents, decide it really is the right passage, and hand it to a language model whose answer ends up in real professional advice. That whole path is yours: how documents get parsed, chunked and embedded, how search combines meaning with exact terms, how results get reranked, and how an agent decides what to read next and when it has read enough. This is where AI products fail without anyone noticing. The answer reads well, the citation is wrong, and the client is the one who finds out.

It isn’t CRUD work, and it isn’t a demo notebook either. Retrieval is where AI products quietly fail: the answer reads well, the citation is wrong, and nobody notices until a client does. Your job is to stop that happening, and to be able to show with numbers that it isn’t happening. You’ll make architecture calls early and live with them.

The role is fully remote. Work from anywhere in the EU.

What You’ll Do

• Own the retrieval pipeline end to end: document parsing and chunking, embeddings, indexing, and keeping all of it current as clients add and change material. Exposed through FastAPI, with ingestion and reindexing running as background jobs.
• Design how we search. Combining semantic and keyword retrieval in Qdrant, fusing ranked lists, filtering on metadata, and reranking so the handful of results we pass to the model are the right ones.
• Build agentic retrieval: query decomposition, the tools a model uses to search and navigate documents, multi-step loops that know when to stop, and the cost and latency budgets that keep them honest.
• Build the evaluation layer that tells us any of this is working: golden sets, retrieval metrics, regression tests on realistic client data, and tracing good enough that a bad answer leads you back to the chunk that caused it.
• Ship it as fast, dependable services in Python and FastAPI, with the heavy work - ingestion, embedding, reindexing - running as background jobs that hold up under load.
• Take data security and isolation seriously. Clients hand us privileged material, and tenants stay strictly separated.
• Make retrieval hold up across our clients’ languages as well as it does in English. Compounding and inflection break sparse retrieval in ways an English eval set never shows you.

Who You Are

• At least five years building backend systems that run in production, and at least two of them shipping retrieval or RAG systems real users depend on. Backend depth without production retrieval won’t be enough for this role, but our Senior Backend Engineer role might be the better fit.

• You’ve diagnosed a retrieval regression in production and fixed it. You can tell us what broke, how you found it, and what the numbers were before and after. - You’ve built and maintained a golden set. How many queries, who labelled them, which metrics you trust, and a change you shipped or killed because of what they told you.

• You’ve run a vector index in production: picked index parameters, dealt with the memory and latency trade-offs, and reindexed without taking search down.

• Strong Python. Comfortable reasoning about FastAPI or a close equivalent, PostgreSQL and Redis under load.

• You don’t ship a retrieval change because the output looked better on the three queries you tried by hand.

• You own things end to end — including the boring maintenance and the tech debt nobody assigned you — rather than building the interesting part and handing off the rest.

• You track what’s moving in vector databases and LLMs because you’re curious, not because it’s the job. Show us the side project, the benchmark you ran for fun, or the repo where you tried something before it showed up in everyone else’s stack.

• You’ve worked with AI coding assistants and have a view on where they help and where they don’t. If your current employer forbids them, that’s not a mark against you. Tell us how you’d review AI-written code instead.

• You’re fine in a startup that changes direction. Decisions get made, then revisited.

Experience we expect with the stack:

• Python: 5+ years
• FastAPI: 2+ years
• Vector databases in production (we run Qdrant): 2+ years. You’ve picked index parameters, dealt with the memory and latency trade-offs, and reindexed without taking search down.
• Embedding models, and the metrics you use to judge retrieval quality
• PostgreSQL / SQL
• OCR-heavy document ingestion at scale; an information-retrieval background (BM25, NDCG, recall@k); search abstractions spanning more than one backend.

The hiring process

• Stage 1: Online coding challenge
• Stage 2: Screening Call
• Stage 3: Technical home assessment
• Stage 4: Whiteboard challenge and presentation of take home assessment
• Stage 5: CEO interview
  Why Join Us?
• Fully remote across the EEA, Norway included. We employ through our own entity or a local employer of record depending on where you are, so ask about your country and we’ll tell you straight away whether we can do it.
• You’ll need the existing right to work where you live. We don’t sponsor visas for this role.
• Be a driver of innovationin one of the most exciting AI ventures
• Work with talented peersin a collaborative, high-energy team
• Shape both product and cultureas we grow
• Flexible, English-speaking environment