Senior FastAPI Developer

Newcode.ai; Oslo; On-site; NOK 900,000 - 1,300,000; Full time

Benefits offered by this job

Flexible, English-speaking environment

Job summary

Newcode.ai is seeking an experienced backend engineer to own the API and data pipelines that power our AI features in production Oslo. You will design and run the orchestration between our product and language models, handling retrieval over large document sets, streaming results, and long-running jobs with reliability.

The role focuses on robust, secure, scalable backend systems, with exposure to RAG, tool-calling, and embeddings.

Qualifications

• 7+ years building production-grade backend systems.
• Ability to design reliable, scalable systems with security in mind.
• Experience with LLM-powered architectures (RAG, tool-calling, agents) or eagerness to learn.
• Comfort in a startup, willingness to make and revisit decisions.
• Experience with async and distributed workloads.

Responsibilities

• Design and build the APIs and services our products run on.
• Work on the AI plumbing: retrieval, orchestration, tool-calling, response streaming, and the evals that tell us whether the output is any good.
• Keep async and distributed work reliable: document ingestion, embeddings, and long-running jobs on Redis.
• Build integrations with the systems clients already use, like email and document stores, and ensure they hold up under load.
• Take data security and isolation seriously, since clients hand us confidential material.

Skills

Python

Backend development

Tools

FastAPI

PostgreSQL

SQL

Redis

Job description

Who are we?

We build AI tools for firms in legal and professional services: software people use for real work, not demos. We started a few months ago and already have paying clients who rely on what we ship. The team is small and moving fast.

The role

You'll own the backend behind our AI features.That'sthe APIs, the data pipelines, and the orchestration sitting between our product and the language models doing the work. In practice it means running retrieval over large sets of documents, getting dependable results out of LLMs and their tool calls, streaming responses to the UI, and processing long jobs in the background without things falling over.

Itisn'tCRUD work. The hard parts here are keeping AI systemsaccurateand fast with confidential data, at production scale.You'llmake architecture calls early and live with them.

What You'll Do

• Designing and building the APIs and services our products run on.

• Working on the AI plumbing: retrieval, orchestration, tool-calling, response streaming, and the evals that tell us whether the output is any good.

• Keeping async and distributed work reliable: document ingestion, embeddings, and long-running jobs onRedis.

• Building integrations with the systems clients already use, like email and document stores, and making them hold up under load.

• Taking data security and isolationseriously, sinceclients hand us confidential material.

Who You Are

• At least seven years building backend systems that run in production. Depth matters more to us than the number.

• You think about how things fail, not just how they behave wheneverything'sfine.

• You'vebuilt real LLM-powered systems, oryou'reitching to: RAG, tool-calling, agents. You know where they tend to break.

• You'refine in a startup that changes direction. Decisions get made, then revisited.

Experience we expect with the stack:

• Python: 6+ years

• FastAPI: 3+ years

• PostgreSQL / SQL

• Redis: 2+ years

Nice to have: RAG or vector search experience;LangChainorLlamaIndex; streaming over SSE, WebSocket orSignalR; Microsoft Graph and email integration work.

Visa Sponsorship:

At this time, Newcode is unable to provide visa sponsorship. Candidates must be authorized to work in the applicable country without employer sponsorship.

Why Join Us?

• Be a driver of innovationin one of Oslo's most exciting AI ventures
• Work with talented peersin a collaborative, high-energy team
• Shape both product and cultureas we grow
• Flexible, English-speaking environment