Descrizione:
hlpy, born in 2020, is a roadside assistance company founded by visionaries who saw a gap in the market and redefined the industry with a cutting-edge digital solution.
What started as a bold idea in Italy quickly expanded to France, Spain, and Germany! As we continue to scale globally, our ambition and market demand propel us toward becoming a major force in the sector.
Are you ready to be part of this journey?
Mission
We are looking for an experienced, hands-on AI Engineer to strengthen our AI team. You will partner with our current AI Engineer to scale our agent ecosystem — taking ownership of the LLMOps infrastructure, building robust evaluation pipelines, and independently delivering the tooling and integrations our agents depend on. Be ready to develop APIs and MCP servers to integrate our agents with our ecosystem, and to operate confidently across the full stack. Guaranteeing quality and reliability.
Key Responsibilities
1. Agent Development, Benchmarking & Evaluation
Co-own the backlog of agent development requests, from scoping to production delivery.
Design and build new agents and enhance existing ones, sharing ownership with the current AI Engineer.
Bring your own perspective on agentic architecture, patterns, and trade-offs via agentic system benchmarks.
2. LLMOps Framework
Own the design and implementation of our LLMOps infrastructure: define metrics to track agent accuracy and detect performance degradation over time.
Build automated monitoring pipelines that triggers when the agent’s accuracy degrades.
Build and maintain large-scale evaluation datasets from real production cases to rigorously test new agents and enhancements before release.
3. Tooling & Integrations
Independently implement and test the tools that agents rely on APIs, MCP servers, third-party integrations, and product-level connections.
Ensure integrations are robust, well-tested, and production ready.
Evaluate emerging tools and libraries, balancing speed of delivery with reliability.
Required Skills & Experience
Master's Degree in Computer Science, AI, or Statistics.
Solid full-stack software engineering background with several years of professional experience.
Proven experience working with LLMs and AI agent frameworks in production.
Strong understanding of LLMOps: evaluation pipelines, prompt testing, observability, continuous monitoring.
Proficient in designing, building, and consuming APIs and integrations (REST, MCP) independently.
Comfortable with DevOps and IaaS practices: containerization (Docker), CI/CD pipelines, and infrastructure automation.
Hands-on, delivery-oriented mindset — you ship things and take ownership.
Nice to Have
Experience building evaluation harnesses and dataset-driven testing at scale.
Previous experience in an AI team or AI-focused product company.
GitHub repositories showcasing relevant work.
Recruitment Process
An Interview with Betty from the People team.
An interview with our tech leadership team to deep dive into your technical experience via case study exercise.
What We Offer
Fresh fruit and good snacks to share with your nice colleagues
Training budget
Remote Working
PLEASE SEND YOUR CV IN ENGLISH