onsite
Senior AI Software Engineer LLM & RAG Systems - Nash Technologies Germany GmbH
Software Engineer
Lead the design and deployment of LLM‑driven RAG solutions, building scalable, cloud‑native pipelines with Python, AWS, and containerization.
About the role
Key Responsibilities
- Architect and implement end‑to‑end LLM and RAG pipelines, integrating retrieval back‑ends and fine‑tuning models for domain‑specific use cases.
- Develop production‑grade services in Python, containerize with Docker, and deploy on AWS (ECS/EKS, Lambda, S3, SageMaker).
- Collaborate with data scientists to curate and preprocess large‑scale datasets, ensuring data quality and compliance.
- Optimize model inference performance, manage resource allocation, and monitor system health using CloudWatch and Prometheus.
- Write clean, testable code, maintain CI/CD pipelines, and enforce best practices for version control and documentation.
Requirements
- 5+ years of software engineering experience with a focus on AI/ML systems.
- Proficiency in Python, deep learning frameworks (PyTorch/TensorFlow), and experience with LLMs (e.g., GPT, LLaMA).
- Hands‑on experience building RAG architectures and integrating vector databases (Pinecone, Milvus).
- Strong cloud background (AWS) and container orchestration (Docker, Kubernetes).
- Excellent problem‑solving skills, ability to work independently, and strong communication in English.
Skills
pythonmachine learningawsdocker