AI Agent & Copilot Engineer

What we're working on: At Lumenalta, we help global enterprises build and scale digital products powered by high-volume, high-impact data. Our work spans modern cloud data platforms, complex transformation pipelines, and real-time business insights. Now, we’re extending that foundation into Generative AI, crafting intelligent systems that don’t just analyze data—they create with it. We’re building AI agents, copilots, and LLM-powered services that integrate deeply into enterprise workflows, especially in complex domains like banking and financial services. If you're passionate about applied AI and ready to work on real-world deployments of cutting-edge tech, this is your opportunity. What You’ll Do Design and develop intelligent AI agents and copilots for tasks ranging from internal productivity boosters to customer-facing automation Build and deploy applications powered by LLMs (e.g., OpenAI, Claude, Mistral, LLaMA, open-source models) Fine-tune and adapt models using LoRA, prompt engineering, RAG, and embedding-based retrieval techniques Collaborate closely with product, data, and engineering teams to ship end-to-end GenAI solutions Develop robust pipelines for model evaluation, safety guardrails, and iterative experimentation Leverage modern frameworks and tooling: LangChain, Hugging Face, Pinecone, Weaviate, Vector DBs, etc. Continuously explore and adopt emerging best practices in GenAI performance, cost optimization, and model governance What We’re Looking For 5 years of software engineering experience, ideally building production-grade, scalable systems Proficient in Python and/or JavaScript/TypeScript (Node.js, React)—we welcome strong JS devs eager to go deep into AI Hands-on experience developing and deploying LLM-powered applications or copilots Experience with transformer architectures, embeddings, vector search, or open-source LLMs Strong command of cloud infrastructure (AWS, GCP, or Azure), Docker, and CI/CD workflows Comfort working in ambiguous, fast-moving environments where learning and iteration are constant Experience with RAG pipelines, vector databases, or LangChain Familiarity with AI safety frameworks, prompt evaluation, or responsible model use in regulated industries (e.g., banking) EU-based candidates only (working remotely within the EU time zones) Ongoing recruitment – no set deadline. J-18808-Ljbffr

Location: Pomezia, Lazio, IT

Posted Date: 9/17/2025