Lead AI Engineer

LHH; Valenzano; In loco; EUR 60.000 - 80.000; Tempo pieno

Descrizione del lavoro

Un'azienda internazionale leader nel settore strategico cerca un Senior AI Engineer per guidare la progettazione e l'implementazione di sistemi AI complessi. I candidati devono avere almeno 8 anni di esperienza nel settore software e competenze avanzate in Python, LangChain e sistemi multi-agente. Lavorando in un ambiente inclusivo, contribuirai a progetti innovativi e guiderai team attraverso sfide tecniche, tutto mantenendo l'attenzione alla crescita e al mentoraggio di altri ingegneri.

Competenze

• 8+ anni in ingegneria software, ingegneria AI/ML o campi correlati.
• 3+ anni di esperienza con LLM e sistemi multi-agente.
• Esperienza comprovata nell'architettura e spedizione di sistemi AI di produzione su larga scala.
• Esperienza nella conduzione di progetti tecnici.

Mansioni

• Progettare e implementare l'Orchestratore di Agenti AI.
• Costruire sistemi di flusso di lavoro stateless.
• Collaborare con ingegneri e data scientist per l'integrazione.
• Mentorare ingegneri AI e supportarne la crescita tecnica.

Conoscenze

Python esperto

LangChain

LLM APIs

FastAPI

Database vettoriali

Database a grafo

Descrizione del lavoro

For our client, international strategy company leader in SAAS applications, we are looking for an :

Senior AI Engineer

The resource will lead the design and implementation of the Co-Pilot's orchestration layer - the intelligent backbone that powers the multi-agent reasoning system. The candidate will be the technical architect who translates the ambitious product vision into a scalable, production-ready AI infrastructure.

Responsabilità

Key Responsibilities Architecture & System Design (40%)

Design and implement the AI Agent Orchestrator using LangGraph / LangChain and the Model Context Protocol (MCP).

Architect a stateful workflow system to manage document processing, agent lifecycles, and human-in-the-loop interactions.

Define agent communication protocols, JSON-based data schemas, and the lifecycle management framework.

Build an Agent Registry for versioning, discovery, and dynamic routing of specialized agents.

Design fault-tolerant workflows with retries, fallbacks, partial-result preservation, and rollback mechanisms.

Create a multi-model routing layer to balance latency, cost, and accuracy across GPT, Claude, Gemini, and open-source models.

Implementation & Development (30%)

Build the Agent Executor to manage reasoning loops, retrievals, and validation tasks.

Develop core System Agents (e.g., Query Understanding, Context Retrieval, Reasoning, Memory, Validation).

Implement an asynchronous execution framework using RabbitMQ / Kafka / SQS for long-running workflows.

Create prompt management tools for versioning, A / B tests, and regression testing.

Develop observability pipelines with OpenTelemetry, LangSmith, and custom telemetry for tracing agent activity.

Integration & Collaboration (20%)

Partner with the Knowledge Graph Engineer to combine vector search and graph-based reasoning.

Work with Data Scientists to embed their prompts and reasoning chains into the orchestration layer.

Collaborate with frontend engineers to design WebSocket and REST APIs for real-time agent interactions.

Integrate with backend services for ETL pipelines, validation utilities, and memory / session management.

Leadership & Strategy (10%)

Lead design and architecture reviews for the AI services layer.

Evaluate and adopt emerging AI frameworks, models, and tools.

Define code standards, testing practices, and documentation guidelines for multi-agent systems.

Contribute to roadmap and sprint planning, aligning product vision with delivery milestones.

Mentor AI engineers and support their technical growth.

Profilo

Experience & Background

• 8+ years in software engineering, AI / ML engineering, or related fields
• 3+ years working with LLMs, multi-agent systems, or agentic AI architectures
• Proven track record of architecting and shipping production AI systems at scale
• Experience leading technical projects or small engineering teams

Technical Skills

• Expert-level Python with strong async / await patterns and type hints
• Deep experience with LangChain, LangGraph, or similar agent orchestration frameworks
• Production experience with LLM APIs (OpenAI, Anthropic, Google) and understanding of prompt engineering, temperature / token controls, and cost optimization
• FastAPI or similar async web framework experience
• Hands-on experience with vector databases (Weaviate, Pinecone, FAISS, Chroma) and semantic search
• Familiarity with graph databases (Neo4j, TigerGraph) and query languages (Cypher, SPARQL)

«I candidati, nel rispetto del D.lgs. 198 / 2006, D.lgs. 215 / 2003 e D.lgs. 216 / 2003, sono invitati a leggere l’informativa sulla privacy consultabile sotto il form di richiesta dati della pagina di candidatura (Regolamento UE n. 2016 / 679).

L’offerta è rivolta a candidati di entrambi i sessi, nel rispetto del D.lgs. 198 / 2006 e della normativa vigente in materia di pari opportunità. L’azienda promuove un ambiente di lavoro inclusivo e garantisce pari opportunità a tutte le persone, indipendentemente da genere, età, origine, orientamento sessuale or disabilità.»