About the role
Responsibilities:
- Design and deploy scalable LLM-powered features such as document analysis, summarisation, and intelligent drafting.
- Build and optimise Retrieval-Augmented Generation (RAG) pipelines and agent-based AI systems.
- Develop distributed, low-latency AI services with strong performance and reliability standards.
- Implement evaluation frameworks, monitoring systems, and experimentation platforms for continuous improvement.
- Collaborate with product and engineering teams to ship secure, production-ready AI solutions at scale.
Requirements:
- 6+ years of experience in AI/ML engineering with production deployment of LLM-based systems.
- Strong expertise in Python, transformer models, prompt engineering, and API-based LLM integration.
- Experience with vector databases, distributed systems, and cloud infrastructure (AWS/GCP/Azure).
- Hands-on experience with MLOps, containerization (Docker/Kubernetes), and CI/CD pipelines.
- Strong problem-solving skills with a focus on performance optimisation, scalability, and reliability.