onsite
AI Software Engineer - Agentic Systems & RAG - Esprit Engineering
Software Engineer
Lead the design and deployment of agentic AI systems that leverage Retrieval-Augmented Generation to deliver intelligent, context-aware solutions using Python, ML, and cloud services.
About the role
Key Responsibilities
- Architect and implement agentic AI pipelines that integrate Retrieval-Augmented Generation (RAG) with large language models.
- Develop and maintain scalable Python services for data ingestion, indexing, and real‑time inference.
- Collaborate with data scientists to fine‑tune models, evaluate performance, and iterate on architecture.
- Deploy solutions on AWS, ensuring high availability, security, and cost efficiency.
- Document design decisions, create technical specifications, and mentor junior engineers.
Requirements
- Strong experience in Python and modern ML frameworks (PyTorch, TensorFlow).
- Hands‑on knowledge of RAG, vector databases, and LLM fine‑tuning.
- Proficiency with AWS services (S3, Lambda, SageMaker, ECS/EKS).
- Excellent problem‑solving skills and a passion for cutting‑edge AI research.
- Effective communication and teamwork in a fast‑paced environment.
Skills
pythonmachine learningnlpaws