remoteonsite
GenAI/Agentic AI Engineer - Persistent Systems
AI Engineer
Lead the design and deployment of generative and agentic AI solutions using Python, PyTorch, and LangChain on AWS, building scalable, containerized services that power next‑generation intelligent applications.
About the role
Key Responsibilities
- Architect and develop end‑to‑end GenAI and agentic AI pipelines, integrating large language models with custom business logic.
- Implement and optimize PyTorch models, fine‑tune embeddings, and manage model lifecycle in a cloud environment.
- Build modular, containerized services with Docker and orchestrate deployments on AWS (ECS/EKS, SageMaker).
- Collaborate with data scientists and product teams to translate business requirements into scalable AI solutions.
- Ensure robust monitoring, logging, and security compliance for AI workloads.
Requirements
- 5+ years of software engineering experience with a focus on AI/ML.
- Proficiency in Python, PyTorch, and experience with LangChain or similar frameworks.
- Hands‑on experience deploying AI services on AWS, including container orchestration.
- Strong understanding of generative models, prompt engineering, and agentic AI concepts.
- Excellent problem‑solving skills and ability to work in a fast‑paced, collaborative environment.
Skills
pythonpytorchlangchainawsdocker