Senior Applied AI Engineer
Germany
United KingdomJob Description
Key Skills Required
Master these to land this role
Want to know if you're a match for this job?
About JUPUS: JUPUS is one of the fastest-growing and most innovative legal tech companies in Europe, on an ambitious mission to rebuild how law firms operate using the power of generative AI. Our core platform introduces autonomous AI teammates designed to automate complex multi-step workflows, manage document understanding, and provide high-fidelity conversational interfaces over detailed legal case files. By combining practical engineering with advanced language models, JUPUS breaks down traditional operational bottlenecks, allowing lawyers to deliver exceptional legal services with less stress, shorter hours, and elevated productivity.
Position Overview
We are seeking a highly autonomous, systems-fluent, and development-oriented Senior Applied AI Engineer to expand our core AI engineering vertical under a permanent, full-time remote layout within Germany or the United Kingdom. In this high-leverage software design seat, you will hold absolute technical ownership over architecting and deploying applied generative AI capabilities directly into a production environment. Shifting completely away from routine non-regulated administrative data entry loops, basic web content formatting, or simple prompt engineering API tickets, you will run an active production-grade Retrieval-Augmented Generation (RAG) pipeline, multi-step agentic workflow framework, and LLM observability laboratory. Reporting directly to the AI Lead, you will collaborate close-knit beside the Head of Engineering, CTO, and Product teams to ship reliable, user-facing features that extract immediate value from complex legal assets. This position requires an engineering authority with 4+ years of professional AI history who handles software layers fluidly natively using AI Engineer, Python, and Backend primitives, commands complete operational intimacy with evaluation tools, and resides within the CET -2/+2 time zone parameters.
Key Responsibilities
- Generative AI Infrastructure Governance: Architect, implement, and optimize production-ready generative AI configurations and LLM orchestration logic across our core product suite natively utilizing AI Engineer best practices.
- Agentic Workflow Instrumentation: Design, develop, and scale sophisticated multi-step AI agents and tool-use systems that automate complex corporate legal processes inside the JUPUS platform.
- Advanced RAG Pipeline Control: Build, calibrate, and maintain high-fidelity RAG architectures—encompassing advanced vector embeddings, intelligent document retrieval nodes, and semantic re-ranking systems natively deploying Python.
- LLM Observability and Evaluation: Establish rigorous testing, evaluation, and logging pipelines across distributed language networks using enterprise monitoring tooling (such as LangSmith or Langfuse).
- Production Feature Integration: Partner close-knit beside product and frontend squads to smoothly embed advanced document understanding and conversational interfaces into live product workflows natively leveraging Backend setups.
- Technical Practice Standardization: Formulate development baselines, code validation patterns, and structural model benchmarking to enforce continuous improvement across all product channels.
- Abstract Concept Translation: Act as a technical advisor, translating complex machine learning techniques and modern AI limits into practical, high-value product roadmaps for cross-functional stakeholders.
- End-to-End Problem Ownership: Initially handle development hands-on as a premier technical contributor inside a small, hyper-growth engineering cell where developers own engineering challenges end-to-end and ship code quickly.
Required Skills & Qualifications
- A minimum of 4+ years of proven, successful professional software engineering history dedicated to building, calibrating, and deploying machine learning or generative AI systems.
- Expert Production AI Command: Verified track record of single-handedly architecting and running production-grade RAG architectures, agentic workflows, or multi-tiered AI agents within user-facing commercial product environments (purely research or academic backgrounds are not matching).
- Deep technical literacy managing LLM orchestration layers beyond basic API integrations—specifically including complex tool registries, custom retrieval logic, and memory structures.
- Outstanding programming mastery in Python coupled with structural software engineering habits (clean testing, profiling, and maintainable data patterns).
- Outstanding written and verbal presentation communication strengths in English, with an established background collaborating with distributed, multi-disciplinary engineering cells.
- Time Zone Context: Position requires uncompromised availability and remote alignment within the CET -2/+2 geographic zone framework. Qualified authorities must reside permanently within Germany or the United Kingdom.
Preferred Strategic Indicators (Nice to Have)
- Prior platform or enterprise background engineering AI applications explicitly inside the legal tech, compliance management, automated contract review, or complex text analytics sectors.
- Meticulous operational intimacy with container tools, cloud hosting multi-tenancy, and high-volume data ingestion parameters.
- An adaptable, high-agency persona characterized by an automation-first focus, a strong desire to ship functional systems rapidly, and an eagerness to create a foundational impact on a hyper-growth brand from the ground up.
What We Offer
- Top-Tier European Legal Tech AI Engineering Remuneration: A highly competitive annual salary package calibrated precisely to your individual systems pedigree and agentic deployment velocity, backed by prominent venture scale funding.
- 100% remote workspace infrastructure autonomy open throughout Germany and the United Kingdom, granting you absolute calendar ownership.
- Foundational AI Revolution Footprint: Elite career landmarks achieved by single-handedly architecting the primary generative networks and core RAG pipelines adopted by Europe’s leading law firms.
- Comprehensive health, medical, and lifestyle preservation setups optimized cleanly to your local residential parameters.
- Access to flat corporate structures with direct leadership visibility to the Head of Engineering and CTO, state-of-the-art MacBook configurations, and wellbeing perks including an Urban Sports Club membership to support an uncompromised healthy lifestyle.
How would you rate this job post?
See what other professionals think about this role.
Safety First
- Never pay for a job application.
- Do not share sensitive bank info.
- Verify the client before starting work.