22 set - Ro
Ntt Data Europe & Latam
Who We AreScorra verso il basso per una panoramica approfondita di questo lavoro e dei requisiti per i candidati. Invii la sua candidatura facendo clic sul pulsante "Candidati".Based in The Romania Excellence Centre, Bucharest - our client is seeking for experienced professionals who value teamwork, pioneering technology, and innovation. People who want to take their careers to the next level of success. You will be part of a global and diverse team, contribute to all stages of software development lifecycle and lead the implementation, deployment and test of multi-agent systems.Also, This Role Will Give You The Chance ToUse frameworks like Google Agent Development Kit (Google ADK) and LangGraph to build robust, controllable, and observable agentic architecturesAssist in the design of LLM-powered agents and multi-agent workflows (planning, tool use, orchestration, memory, and human-in-the-loop)So if you are an experienced AI Engineer please join our team to create the next big thing in digital banking.What You’ll Be DoingDesign and build complex agentic systems with multiple interacting agentsImplement robust orchestration logic (state machines / graphs, retries, fallbacks, escalation to humans)Implement RAG pipelines, tool calling, and sophisticated system prompts for optimal reliability, latency, and cost controlApply core ML concepts to evaluate and improve agent performance, including dataset curation and bias/safety checksLead the development of agents using Google ADK and/or LangGraph, leveraging advanced features for orchestration, memory, evaluation, and observabilityIntegrate with supporting libraries and infrastructure (e.G., LangChain/LlamaIndex, vector databases, message queues, monitoring tools) with minimal supervisionDefine success metrics, build evaluation suites for agents (automatic + human evaluation),
and drive continuous improvementCurate and maintain comprehensive prompt/test datasets; run regression tests for new model versions and prompt changesDeploy and operate AI services in production, establishing CI/CD pipelines, observability, logging, and tracingDebug complex failures end-to-end, identifying and document root causes across models, prompts, APIs, tools, and dataWork closely with product managers and stakeholders to shape requirements, translate them into agent capabilities, and manage expectationsDocument comprehensive designs, decisions, and runbooks for complex systemsWhat We’re Looking ForBachelor’s degree in Computer Science, Engineering, or related fieldAt least 3 years of experience as Software Engineer / ML Engineer / AI Engineer, with at least 1-2 years working directly with LLMs in real applicationsStrong proficiency in Python (core language features, packaging, testing, async, type hints)Very strong software engineering practices: version control (Git), unit/integration testing, code reviews, CI/CDExperience building and consuming REST/gRPC APIs and integrating external tools/servicesUnderstanding of core ML concepts: supervised/unsupervised learning, train/validation/test splits, overfitting, regularization, and common metrics (precision, recall, F1, ROC-AUC, etc.)Good understanding of deep learning basics (neural networks, embeddings) and at least one ML/DL framework (e.G., PyTorch, TensorFlow, JAX,
scikit-learn)Deep practical knowledge of large language modelsTokenization, context windows, temperature, top‑p, system vs user promptsPrompt engineering patterns (ReAct, chain‑of‑thought, tool‑calling/tool‑use)Fine‑tuning / adapters / instruction‑tuning, or experience with RAG as an alternativeExperience building LLM‑powered applications end‑to‑end: from idea → prototype → productionFamiliarity with safety and reliability considerations: hallucinations, guardrails, content filtering, privacyConceptual understanding of modern xysqume agentic frameworks and patterns (stateful graphs, multi‑agent coordination, human‑in‑the‑loop, memory, and evaluation).Hands‑on experience with at least one of: Google Agent Development Kit (ADK) – building multi‑agent workflows, using its orchestration, tools, and evaluation features or LangGraph – designing graph‑based, stateful agent workflows with cycles, branches, and durable executionCandidates must be able to read, reason about, and extend ADK/LangGraph‑based codebasesDirect production experience with both ADK and LangGraph is a strong plusExperience working with vector databases (e.G., Pinecone, Weaviate, pgvector, Chroma) for retrieval‑augmented generationComfortable with SQL and basic data modelingExperience deploying on at least one major cloud platform (GCP, AWS, Azure) and using managed services (e.G., serverless runtimes, container orchestration, secrets management)Nice‑to‑Have Experience WithVertex AI / Gemini or other hosted LLM ecosystemsRelated frameworks and tools: LangChain, LlamaIndex, semantic search, evaluation frameworks (e.G., RAGAS, custom eval harnesses)Monitoring and observability stacks (OpenTelemetry, Prometheus/Grafana/NewRelic, Datadog, etc.)#J-18808-Ljbffr
23 set - Lecce
Snai
23 set - Tempio Pausania
Serafina
23 set - Grosseto
Il Globo Vigilanza
23 set - Bolzano
Kpmg Italy