🚀 About Aptendo Aptendo is a boutique IT consultancy and software engineering firm specialized in digital transformation and AI-powered innovation. With globally distributed expert teams, we help scale-ups and medium and large enterprise clients scale fast with niche expertise their digital roadmaps. As we continue to grow our AI capabilities, we’re looking for a passionate LLM Engineer / NLP Specialist to help build next-generation solutions that solve real-world problems — from document intelligence to conversational assistants and enterprise copilots. 🔍 About the Role As an LLM Engineer / NLP Specialist, you will play a key role in designing, fine-tuning, and deploying large language model–based solutions. You’ll work at the intersection of applied AI and enterprise software, helping integrate cutting-edge transformer models into real business applications across sectors like retail, legal tech, and finance. 💼 Key Responsibilities • Fine-tune and adapt foundation models (e.g., GPT, Claude, LLaMA, Mistral) to specific enterprise use cases. • Build and optimize RAG (retrieval-augmented generation) pipelines with vector databases (FAISS, Pinecone, Weaviate). • Develop prompt engineering strategies that ensure relevance, accuracy, and control in outputs. • Work closely with product and engineering teams to deploy LLM services into production environments (chatbots, summarization engines, etc.). • Optimize inference performance and cost using quantization, caching, or parameter-efficient tuning techniques. • Monitor and evaluate model behavior with respect to hallucination, bias, and business relevance. • Stay up to date with advancements in NLP, LLM architectures, and enterprise-ready tooling (LangChain, LlamaIndex, etc.). ✅ Required Qualifications • 3+ years of experience in NLP or ML-focused software engineering roles. • Strong Python skills and experience with frameworks like PyTorch and Hugging Face Transformers. • Hands-on experience with both LLM APIs (OpenAI, Anthropic, Cohere) and open-source models (LLaMA, Mistral, Falcon). • Solid understanding of embeddings, semantic search, and vector stores. • Familiarity with prompt tuning, fine-tuning, and few-shot learning. • Prior work in one or more NLP tasks such as summarization, entity extraction, Q&A, NLU/NLG. • Experience using LangChain, LlamaIndex, or similar frameworks to orchestrate LLM workflows. ➕ Nice to Have • Experience with inference optimization (e.g., LoRA, quantization, PEFT). • Exposure to knowledge graphs, multilingual NLP, or regulated domains (e.g., healthcare, legal). • Background in containerized AI deployment (Docker, Kubernetes) and CI/CD practices. • Open-source contributions or research publications in the NLP or AI space. 💡 Why Join Aptendo? • Work on high-impact AI use cases with enterprise clients across North America, Europe, Middle East and beyond. • Collaborate with a team of top-tier consultants and technologists in a fast-moving environment. • Enjoy flexible work arrangements, remote-first culture, and opportunities for technical leadership. • Be part of a growing company where your expertise directly shapes solutions.