AI Native Software Engineering Specialist
€29k - €55k • Remote • Roma
Posted 27d ago
About the job
You will be responsible for building production-grade agentic AI systems that operate within enterprise environments, moving beyond demos and prototypes to deliver real-world solutions. This role involves designing, building, and deploying these systems across the full enterprise technology stack, working directly with client engineering teams. You will lead technical design sessions and develop reusable patterns and accelerators to ensure scalability. This position offers broad exposure to various industries, technology stacks, and organizational complexities, along with unique access to engineering teams at leading AI companies and a direct path to specialized programs.
Responsibilities
- Design and build production-grade agentic systems, including multi-agent orchestration, RAG pipelines, policy-based routing, tool invocation, memory management, and lifecycle observability.
- Develop and manage RAG pipelines, focusing on embeddings, chunking strategy, vector search, and context window engineering.
- Integrate and abstract across multiple LLM providers (e.g., OpenAI, Anthropic, Vertex AI, open-source models), managing fallback routing, tokens, costs, and latency.
- Implement LLMOps in production, including designing eval harnesses with quality metrics, prompt versioning, and setting up observability tooling for cost and safety monitoring.
- Embed with client engineering teams to design, prototype, and deploy agentic solutions through workshops, proofs of concept, and collaborative coding sessions.
- Create reusable patterns, accelerators, and playbooks to scale solutions and expedite future client engagements.
- Define and utilize metrics to measure agent accuracy, latency, safety, and cost-effectiveness, presenting findings to client stakeholders in business terms.
Requirements
- Hands-on experience designing and deploying agentic AI solutions in a production environment.
- Demonstrated experience with agentic orchestration frameworks like LangGraph, CrewAI, or AutoGen at a production level.
- Direct experience calling LLM APIs (OpenAI, Anthropic, Vertex AI) in production code, including provider abstraction and managing token, latency, and cost tradeoffs.
- Experience with RAG pipeline ownership, including embeddings, chunking strategy, vector databases, and context engineering.
- Understanding of LLMOps fundamentals, such as eval harness design, prompt versioning, and production observability.
- Proficiency in cloud-native engineering practices, including Kubernetes, Docker, microservices, serverless, CI/CD, and IaC (Terraform or Helm).
- Strong Python skills; Java or equivalent backend language is acceptable.
- Experience with production debugging and observability.
- Prioritization of quality of experience over years of experience, with a preference for candidates who have shipped multiple production agentic systems.