Senior AI Engineer

About the team

The Incubate Team explores and implements cutting-edge applications in Agentic AI and Machine Learning. The team is currently building a platform for the safe execution of AI

agents: an environment where autonomous agents can run, call tools, and act on data with isolation, policy enforcement, observability, and human oversight built in. You will join a

small, hands-on team that moves from research idea to working prototype to production-grade component, and you will be expected to own significant parts of that journey.

Experience: 4–5+ years in product development

Location / Work model: Rome (Italy) / Hybrid

Mandate Skills

• Education: Bachelor’s or Master’s degree in Computer Science, Statistics, or a related quantitative field
• Programming: Python (expert level)
• ML / GenAI frameworks: PyTorch, TensorFlow, scikit-learn;
• LangChain, LangGraph, LlamaIndex
• ML architectures: Deep Learning, Generative AI / LLMs, predictive models
• Agentic AI: proven experience designing and shipping LLM-based agents (tool/function calling, multi-agent orchestration, RAG, memory) integrated with external systems via APIs or protocols such as MCP
• Containers & orchestration: Docker, Kubernetes
• Scripting & OS: Bash shell scripting on Linux/Unix

What you will do

• Own the design and delivery of core components of the agent execution platform: agent runtime, tool/function-calling layer, sandboxing and isolation, policy and guardrail enforcement, and audit/observability.
• Build and evaluate GenAI solutions using state-of-the-art and proprietary models; prototype quickly, measure rigorously, and harden what works into production-quality services.
• Define and implement evaluation pipelines and datasets to measure agent correctness, safety, robustness, and cost (e.g., red-teaming, prompt-injection resistance, regression suites).
• Apply data science methods — experiment design, statistical analysis, predictive modelling — to understand agent behaviour and drive product decisions with evidence.
• Package and deploy services as containers on Kubernetes; contribute to CI/CD, monitoring, and operational tooling.
• Provide technical leadership: lead design reviews, set engineering standards for the team, and mentor less experienced engineers.
• Collaborate with product, security, and platform teams; document designs and share findings through demos and technical write-ups.
• Track the agentic/LLM ecosystem and bring relevant techniques, tools, and research into the team’s roadmap.

What we are looking for:

• BE/BTech or above in Computer Science, Statistics, or related stream; 4–5+ years of product development experience, with a track record of shipping AI/ML features to production
• Extensive experience in AI/ML technologies and professional software development practices (testing, code review, version control, CI/CD)
• Expert-level Python
• Experience developing cutting-edge GenAI solutions, exploring advanced AI models, and working with proprietary generative models
• Hands-on experience with agent frameworks (LangChain, LangGraph, LlamaIndex) and vector/retrieval stacks
• Deep knowledge of Kubernetes and container-based deployment; Docker proficiency
• Bash shell scripting in Linux/Unix environments
• Solid understanding of secure-by-design principles for AI systems: least privilege, sandboxing, input/output validation, secrets handling, auditability
• Ability to take ambiguous problems from concept to working solution with limited supervision
• Excellent written and verbal communication skills; able to explain complex technical trade-offs to mixed audiences

Nice to have

• Java (or another JVM language) for integration with existing services
• Experience with MLOps/LLMOps tooling (model serving, experiment tracking, evaluation frameworks)
• Familiarity with agent interoperability protocols (e.g., MCP, A2A) and tool/plugin ecosys