Senior AI Engineer
Se i requisiti e l'esperienza richiesti per questo lavoro corrispondono alle sue competenze, la preghiamo di candidarsi tempestivamente.Aptus.AI · Pisa, Italy (Hybrid)About Aptus.AIAptus.AI is building the next generation of AI for the legal and compliance industry. Our platform combines frontier language models with deep domain expertise to help legal professionals and compliance teams work faster, more accurately, and with greater confidence. We operate at the intersection of cutting-edge AI research and the rigorous demands of the legal world, and we're growing fast.About the RoleWe're looking for an AI Engineer who has already built real AI agents, not just integrated an LLM API, but designed and shipped systems that reason, plan, and act autonomously. You'll work at the core of our product, designing the multi-agent architectures that power our compliance and legal AI assistants.This role sits at the intersection of systems design, applied AI, and product engineering. You'll collaborate directly with our product and engineering leads to translate complex legal workflows into robust agentic pipelines, and you'll own those systems end to end, from architecture to production.We're looking for someone who thrives in ambiguous, fast-moving environments, picks up new technical domains quickly, and holds themselves to a high bar for code quality and system reliability.ResponsibilitiesDesign and implement multi-agent systems for legal and compliance use cases, including orchestration patterns, tool use, memory, and state managementOwn agentic pipelines end to end: from requirements and architecture through deployment and iterationWork closely with product, legal domain experts, and customers to understand workflows and translate them into technical solutionsPrototype quickly, gather real-world feedback, and iterate with disciplineContribute to architectural decisions and help establish engineering best practices for AI systemsCommunicate clearly with both technical teammates and non-technical stakeholders about system behavior, trade-offs, and progressYou may be a good fit if youHave already designed and shipped AI agents in production, systems that plan, use tools, and operate with meaningful autonomyHave a solid grasp of agent orchestration patterns (ReAct, multi-agent delegation, tool-calling loops, routing, parallelism, etc.)Write clean, maintainable code and have strong software engineering fundamentalsCan quickly develop deep understanding of complex, unfamiliar technical or legal domainsAre proficient with modern web technologies (e.g. Python, TypeScript) and comfortable working across the stackCommunicate effectively with both technical and non-technical stakeholders, you can explain what an agent is doing and why to a lawyer as clearly as to an engineerHave a high tolerance for ambiguity and a bias toward actionStrong candidates may also haveExperience with LLM orchestration frameworks (LangGraph, LlamaIndex, CrewAI, custom implementations, etc.)Familiarity with RAG architectures and vector databases (e.g. Pinecone, Weaviate)Background in legal, compliance, or other regulated domainsExperience building internal tooling or developer-facing platformsExposure to streaming architectures and real-time UI patterns for LLM outputA history of iterating directly with end users and incorporating feedback into system designHands-on experience with AWS services relevant to AI workloads (e.g. S3, Lambda, ECS/EKS, SageMaker, IAM) and comfort navigating cloud infrastructure independentlyRepresentative ProjectsHere's the kind of work you'd own at Aptus.AI:Designing a multi-agent pipeline that routes legal queries to specialized sub-agents (case law retrieval, regulatory analysis, document drafting) and synthesizes a coherent responseBuilding an AI compliance assistant grounded in a proprietary risk matrix, capable of answering structured and open-ended questions about corporate liabilityCreating the orchestration layer that decides whether a query needs fast single-step reasoning or a deeper, iterative research workflowDeveloping full-stack tooling that lets non-technical legal experts inspect, evaluate, and give feedback on AI agent outputsWhy Aptus. xpavfwm AILegal AI is one of the most consequential domains where AI can have real impact, the work mattersYou'll have high ownership and direct influence on product and architecture from day oneWe're based in Pisa with a highly-flexible hybrid setupWe encourage applications from candidates who don't meet every single requirement. If you're excited about the problem and bring strong fundamentals, we want to hear from you.