onsite
Gen AI Engineer - RigelSky
AI Engineer
Lead end‑to‑end development of generative AI solutions, building RAG pipelines, vector search, and AI agents using Python, PyTorch, and cloud MLOps platforms.
About the role
Key Responsibilities
- Design, implement, and maintain large‑scale generative AI models and RAG pipelines in Python.
- Integrate vector databases (Pinecone, ChromaDB, FAISS) for semantic search and retrieval‑augmented generation.
- Develop AI agents and microservices, exposing REST APIs and deploying via Docker and Kubernetes.
- Collaborate with data scientists to fine‑tune models, evaluate performance, and iterate on prompt engineering.
- Implement MLOps workflows: CI/CD, monitoring, and automated testing across AWS, Azure, and GCP.
Requirements
- 9+ years of experience in AI/ML engineering with a strong focus on generative models.
- Expertise in cloud MLOps, containerization, and orchestration (Docker, Kubernetes).
- Strong problem‑solving skills and ability to work independently in a W2 contract environment.
Skills
pythonragpytorchmlops