Time since we first saw it
Day 172
Up longer than most. Similar jobs usually come down between day 1 and day 15.
From 1,371 similar postings that came down. Coming down is not always a hire.
Berlin · Münzstraße 21, 2. Etage 10178 Berlin, Germany
Open 5 months, first seen by us 172 days agoLocation type: HybridFrom the employer’s posting
Employment type: Full-timeFrom the employer’s posting
Department: EngineeringFrom the employer’s posting
You will work closely with Product and Engineering to turn complex, unstructured problems into robust, production-ready AI solutions.
Build the evaluation infrastructure: test datasets, regression checks, quality metrics tied to business outcomes
Collaborate with Product to scope ambiguous problems into something an AI pipeline can actually solve reliably
Your Role As a Senior AI Product Engineer at Voyfai, you will own LLM pipelines that process real logistics documents and data in production, in multiple languages and formats. You will work closely with Product and Engineering to turn complex, unstructured problems into robust, production-ready AI solutions. This role is hands-on and impact-driven. You will take end-to-end ownership from use case discovery and prompt design to deployment, monitoring and continuous improvement in production, with a strong focus on real-world reliability and business impact.
Decide when to use an LLM and when not to. A lot of good engineering here is knowing when a regex, a lookup table, or deterministic code is the right answer Build the evaluation infrastructure: test datasets, regression checks, quality metrics tied to business outcomes Pick models pragmatically across providers (Claude, GPT, Gemini, open-weights) based on cost, latency and quality tradeoffs for each use case
Stay ahead of the curve on prompting techniques and apply them pragmatically to solve hard extraction problems Collaborate with Product to scope ambiguous problems into something an AI pipeline can actually solve reliably Raise the bar on code quality, testing and documentation across the team
Open 5 monthsWe first saw this posting 172 days ago and it is still up. Roles open this long are often slow to fill or kept open to collect applications.
These dates show when we found the posting. Check the employer’s website to confirm it is still accepting applications.
Day 172
Up longer than most. Similar jobs usually come down between day 1 and day 15.
From 1,371 similar postings that came down. Coming down is not always a hire.
1 open job
Add your resume and we’ll mark which of these tools you already use, and point out anything in the posting that could rule you out.
- Strong backend fundamentals: PostgreSQL, async workflows (we use Temporal), queues, observability, CI/CD - Comfort working in both Python (AI pipelines) and TypeScript/Node.js (our product stack) - Deep practical understanding of LLM behaviour: prompting, structured outputs, context window management, common failure modes, handling non-determinism and writing evals that catch regressions before users do
- Several years as a software engineer shipping production systems, with at least 3 years focused on LLM-powered features in production - Strong backend fundamentals: PostgreSQL, async workflows (we use Temporal), queues, observability, CI/CD - Comfort working in both Python (AI pipelines) and TypeScript/Node.js (our product stack)
Complete your application on jobs.ashbyhq.com. The employer’s form will show what is required.
Already applied? Track this application
Join Voyfai, a fast-growing Series A startup shaping the future of logistics and technology across Europe.
Headquartered in Berlin, we operate at the center of a broader group of companies active across several European markets. This is a unique opportunity to take ownership from day one, drive meaningful impact and grow within a dynamic, fast-paced environment. Whether you're shaping processes, building strategies or leading initiatives, your contributions will directly influence the success of Voyfai and the companies we support. If you're passionate about building from scratch and excited to be part of a company on the rise, we'd love to hear from you.
Your Role
As a Senior AI Product Engineer at Voyfai, you will own LLM pipelines that process real logistics documents and data in production, in multiple languages and formats. You will work closely with Product and Engineering to turn complex, unstructured problems into robust, production-ready AI solutions.
This role is hands-on and impact-driven. You will take end-to-end ownership from use case discovery and prompt design to deployment, monitoring and continuous improvement in production, with a strong focus on real-world reliability and business impact.
Key Responsibilities
Design and own LLM pipelines that process real logistics documents and data in production: prompt design, structured output validation, eval harnesses, retries, fallbacks, monitoring, alerting and cost tracking
Decide when to use an LLM and when not to. A lot of good engineering here is knowing when a regex, a lookup table, or deterministic code is the right answer
Build the evaluation infrastructure: test datasets, regression checks, quality metrics tied to business outcomes
Pick models pragmatically across providers (Claude, GPT, Gemini, open-weights) based on cost, latency and quality tradeoffs for each use case
Stay ahead of the curve on prompting techniques and apply them pragmatically to solve hard extraction problems
Collaborate with Product to scope ambiguous problems into something an AI pipeline can actually solve reliably
Raise the bar on code quality, testing and documentation across the team
What You Bring
Several years as a software engineer shipping production systems, with at least 3 years focused on LLM-powered features in production
Strong backend fundamentals: PostgreSQL, async workflows (we use Temporal), queues, observability, CI/CD
Comfort working in both Python (AI pipelines) and TypeScript/Node.js (our product stack)
Deep practical understanding of LLM behaviour: prompting, structured outputs, context window management, common failure modes, handling non-determinism and writing evals that catch regressions before users do
Pragmatic judgment about architecture and tradeoffs. You have seen complex systems get simpler over time
What We Offer
Competitive salary and equity options
A dynamic, fast-paced work environment with a mission-driven team
Flexible working arrangements (Hybrid)
30 days of PTO
Regular team events and offsites
Monthly mobility budget via Navit
New AI Engineer postings at the employers we follow are up 340% over the last 6 weeks compared with the 6 before.
Each bar is one week of new postings. The darkest bars are the last 6 weeks.
Counted from the hiring pages we’ve followed for at least five weeks, so employers we add don’t look like growth. Updated weekly.
We file this job under AI Engineer, by the work the posting describes.
AI engineers build products on top of AI models that already exist, most often large language models: they connect a model to a company's data and tools and ship the assistants, agents and search features people use.
Postings ask for strong Python or TypeScript, experience with model APIs, retrieval and agent frameworks, and ways to test whether the model's answers are good enough.
An ML engineer trains and serves models; an AI engineer usually starts from a model someone else trained and builds the product around it, though titles often mix the two.
Selected passages from the saved posting. Check the full description for conditions and exceptions.
No pay amount identified in the saved description.
Münzstraße 21, 2. Etage 10178 Berlin, Germany
- A dynamic, fast-paced work environment with a mission-driven team - Flexible working arrangements (Hybrid) - 30 days of PTO
No clear work-authorization passage found. Eligibility is unconfirmed.