Forward Deployed Engineer
Posted 17 days ago
The role in short
Embed with law firm clients to map legal processes and build, test, and deploy production AI workflows using the Aurora platform.
Turn how legal work gets done into AI workflows lawyers trust
Newcode helps legal organizations build, govern, and deploy AI workflows connected to their knowledge and existing systems. Our Aurora workflow platform enables teams to turn firm expertise into repeatable workflows that operate within the firm's technology environment.
Our clients are law firms and professional-services teams. They know exactly where their work is slow, repetitive, or risky. What they don't know is how to turn that into an AI workflow they can trust with real client work. We are hiring a Forward Deployed Engineer to do exactly that. This role reports to the Head of Forward Deployed Engineering.
The Opportunity
You'll work directly with clients to understand how their work actually gets done, and then build it in Aurora, our visual AI workflow builder. Aurora is low-code. You design flows by connecting components on a canvas, configure the models, prompts, document search, and integrations, and write a short script where the canvas stops.
The hard part isn't the code. It's understanding a messy process well enough to break it into steps a model can do reliably, seeing where it will fail before it does, and showing a skeptical partner at a law firm that it works.
This role rewards judgment and engineering discipline more than seniority. We care more about how you think than how many years you've written code. You need to be comfortable with hands-on technical work. For example, you can read API documentation to connect two systems, edit JSON files, write a short Python function when the canvas is not enough, and find out why a flow stopped working.
How the team works
You'll report to the Head of Forward Deployed Engineering, who manages the FDEs across our client pods and owns engineering quality, staffing, coaching, and technical delivery practices.
What you will own
- Sit with clients alongside the senior legal engineer and map how a piece of work gets done today: the inputs, the decisions, the exceptions, and who signs off.
- Turn the workflow requirements into working flows in Aurora, such as document intake, clause extraction, contract review, drafting, and multi-step agents.
- Configure the building blocks: prompts, model choice, search over client documents, and connections to the systems clients already use, within each firm's access controls and confidentiality boundaries.
- Write python scripts where configuration isn't enough, such as a custom component, a data transformation, or an API call, and flag the ones worth reusing across clients.
- Test every flow against real examples and the evals agreed with the firm, find where it fails, and fix it before a client finds it. Show with evidence against the legal acceptance criteria, not a demo, that it works.
- Run workshops and pilots, help deliver the AI Academy for each firm's Aurora users, and stay responsible for the flow after it goes live, with a named owner and support plan agreed before release.
- Follow the FDE team's delivery playbook and technical standards, including design and code reviews, testing, traceability, monitoring, and human review suited to each flow's intended use.
- Give realistic estimates, and raise scope changes, risks, and dependencies early with the senior legal engineer and the Head of Forward Deployed Engineering.
- Bring what you learn back, through the Head of Forward Deployed Engineering, to Product and Engineering as patterns rather than anecdotes: missing features in Aurora, recurring requests and how often they come up, and bugs.
- Help the team track delivery time, effort, workflow adoption, and component reuse, so that estimates and client outcomes improve over time.
What you bring
- You think in structure. Give you a vague process and you break it into clear steps, inputs, and decisions, and you see where it will go wrong.
- You learn a new domain fast. You don't need a law degree, but you'll want to understand how a lawyer reviews a contract or runs a due diligence.
- You explain things clearly to a law firm partner and to an engineer, and you're honest about what AI can and can't do.
- You work well in a small team. You take the legal requirements from the senior legal engineer, hold your work to the team's engineering standards, and ask for review early rather than late.
- At least three years in a technical, client-facing role, for example solutions engineer, implementation consultant, technical consultant, automation specialist, or developer.
- Hands-on experience configuring or building in a technical tool: workflow automation, integrations, a low-code platform, or software development.
- You can read and write simple scripts in Python, work with JSON and REST APIs, and debug what you built.
- You use LLMs every day and have a view on prompting, where models are reliable, and where they aren't.
- You're fine in a startup that changes direction. Decisions get made, then revisited, and direction changes to meet the goal.
- Fluent in English.
Additional experience we value
- Experience with n8n, Make, Zapier, Power Automate, or a similar workflow tool.
- Experience building LLM applications, retrieval (RAG), or agents.
- A background in law, consulting, audit, finance, engineering or another professional-services field.
- Experience with document management systems such as iManage or SharePoint.
- Experience with law-firm constraints such as matter permissions and ethical walls.
- Experience with Microsoft Azure.
- We value demonstrated capability over a particular degree or job title.
What success looks like
In your first 30 days, you know Aurora well enough to build, test, and debug a flow on your own, you have joined a client pod, and you have taken part in a discovery workshop and an AI Academy session.
By 60 days, you are building and testing flows on at least one active deployment, following the delivery playbook, with evals, release criteria, and support ownership in place.
By 90 days, you deliver repeatably across multiple clients, and the lawyers and firm technology teams you work with trust your flows with real client work.
Location
Hybrid from one of the locations only: Oslo, Norway; Wroclaw, Poland; or Chicago, United States, 3 days per week in the office. Expect client travel of roughly 25% typically for discovery workshops, pilots, and go-live support. Collaboration with distributed colleagues across time zones, including the Head of Forward Deployed Engineering in Chicago, is part of the role.
Why join Newcode
At Newcode.ai, we specialize in making law firms AI-native through a configurable AI harness designed for the realities of legal work. Achieving that mission takes more than powerful technology: it requires exceptional people who can understand how lawyers work, configure solutions around their needs, and help them realize the immense value AI can create. As part of our collaborative, high-growth team, you'll work side by side with visionary founders at the forefront of AI and legal innovation, shaping both our product and the definition of AI native legal work.
As a Forward Deployed Engineer, you'll work directly with clients on AI that ends up in real legal work, not in a demo. You'll help shape how we deploy Aurora, contributing to the Aurora playbook and the field patterns that make it into the product, and you'll grow with regular coaching from the Head of Forward Deployed Engineering, clear technical standards, and a team that delivers repeatably rather than through individual heroics.
We believe in being transparent about what it's like to work at Newcode.ai. 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, great! Keep reading to learn more.
Company stage. Newcode is a growth-stage legal AI company founded in 2021. It has moved beyond early product validation into scaling deployments and expanding in the U.S. The company describes its product as a configurable AI platform that connects a firm's data, systems, and workflows, with controls for permissions, models, and deployment.
Funding. Newcode has a total funding of $20 million. The Series A was led by OnDean Forward, with participation from The LegalTech Fund, Antiportfolio Ventures, Relativity's investment arm Rel Labs, and existing investors.
Traction and deployments. Today Newcode serves more than 100 law firms and government agencies in Europe and the United States, with annual recurring revenue more than tripling over the prior 12 months. Check out our webpage for our most recent customers.
Why now is a compelling time to join.
Newcode is at an exciting stage of growth. With fresh Series A funding and strong customer and revenue growth, we are investing in the next chapter of our growth in Europe and the U.S.
Our platform is moving beyond standalone AI tools and into the everyday workflows of leading legal teams. From firmwide deployments to integrated legal research, we are helping customers put AI to work on meaningful, real-world challenges.
As we expand our product, customer support, go-to-market, and partnerships, you will have the opportunity to take on important work and help shape how we grow. You will join a global team of more than 60 people, with the scale to serve major organizations and the agility to make a visible impact.
If you are excited to build practical AI for the legal industry and help shape a company's next stage of growth, this is a great time to join Newcode.
Benefits
We offer competitive salary, equity, and bonus across all locations. Benefits are tailored to each country to meet local requirements and market practice:
- US (Chicago): Medical, dental, and vision; 401(k); paid time off;
- Norway (Oslo) and Poland (Wrocław): Statutory benefits plus local offerings, including pension, paid leave, and parental leave
The hiring process
- Stage 1: Screening call (15 minutes)
- Stage 2: Case assessment: design and build a flow for a realistic client problem (1 hours)
- Stage 3: Presentation of your case to the team, including the Head of Forward Deployed Engineering (3 hours)
- Stage 4: CEO interview (15 minutes)
Newcode is an equal opportunity employer and welcomes applicants of all backgrounds.
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.
Prep for this interview
5 questions likely to come up at Newcode, each matched to a line in this posting.
- 1LLMs, RAG and agents
They wrote: “You use LLMs every day and have a view on prompting, where models are reliable, and where they aren't.”
The model gives a confident wrong answer to an important customer. What now?
How to answer
Why they ask: Tests how you handle trust, on top of the technical fix.
- Tell the customer the same day what you know and when they'll hear more
- Reproduce it and find the cause (bad retrieval, missing data, prompt, model)
- Add the case to the test set so it can't come back unnoticed
- Add a guard where it matters: citations, confidence checks, human review
Tip: Own it with the customer first, then show the change that stops it happening again.
- 2Discovery and scoping
They wrote: “Turn the workflow requirements into working flows in Aurora, such as document intake, clause extraction, contract review, drafting, and multi-step agents.”
A customer says “we want AI in our claims process.” What do you ask in the first meeting?
How to answer
Why they ask: Most FDE work starts this vague. They want to hear you find the real problem before you pick a tool.
- Map the current process: who touches a claim, in what order, with which systems
- Find the slowest or most error-prone step and ask what it costs them
- Agree on one measurable goal (for example time per claim, or error rate)
- Ask what data you can access, and who signs off on security
Tip: Ask about the work, not the technology. Who does it today, how long it takes, what a mistake costs, and how they'd know it got better.
- 3Integrations and APIs
They wrote: “Write python scripts where configuration isn't enough, such as a custom component, a data transformation, or an API call, and flag the ones worth reusing across clients.”
Walk me through connecting our product to a customer's internal system that has no documentation.
How to answer
Why they ask: This happens weekly in the job. They want a calm, step-by-step method.
- Find who owns the system and get read access to a test environment
- Watch real traffic or logs to learn the data shapes
- Build a thin adapter with logging around every call
- Agree on how failures get reported, and who fixes what
Tip: Talk about finding the owner of the system first. The code is the easy part.
- 4Coding
They wrote: “You think in structure. Give you a vague process and you break it into clear steps, inputs, and decisions, and you see where it will go wrong.”
Build a small in-memory cache. Then add expiry. Then a size limit.
How to answer
Why they ask: Staged exercises show how your code holds up when requirements change mid-interview, like at a customer.
- Start with get and set on a dictionary, plus tests
- Store an expiry time with each value and check it on read
- Track use order and evict the least recently used entry when full
- Say what you'd change for many threads or many machines
Tip: Keep the first version simple and well tested so the next stage is a small change.
- 5Ownership and working with customers
They wrote: “By 60 days, you are building and testing flows on at least one active deployment, following the delivery playbook, with evals, release criteria, and support ownership in place.”
Tell me about something you shipped that broke in production.
How to answer
Why they ask: Everyone has broken production. They want to hear you own it and change something afterwards.
- What broke and who it affected
- How you found out and what you did in the first hour
- The root cause, said plainly
- What you changed so it can't happen the same way again
Tip: Pick a real one with a cost. Spend most of the answer on what you changed.
Not the one? Get the next one by email
New roles land here every day. Pick what you want to hear about.
Want the job, not just the posting? Learn how FDEs work.
FDE Info is our free weekly newsletter for forward deployed engineers: tools, field notes from real deployments, and how FDE teams hire and pay.
Free. One email a week. Unsubscribe in one click.