Description
You will design, prototype, and implement LLM-based systems.
Responsibilities
- Design, prototype, and implement LLM-based systems, including RAG pipelines, fine-tuning, and prompt engineering.
- Lead evaluation and integration of foundation models (OpenAI, Claude, Mistral, Meta, etc.) and open-source alternatives (LLaMA, Falcon, etc.).
- Architect LangChain, Haystack, or similar frameworks for orchestration of tool use and agentic workflows.
- Collaborate with cross-functional teams (Data, DevOps, Product, Security) to integrate GenAI into enterprise systems securely and at scale.
Required Skills
- 8+ years of professional experience.
- Expert proficiency in Python.
- Hands-on experience with RAG implementation.
- Deep knowledge of Gen AI concepts and practices.
- Experience with foundation models (e.g., OpenAI, Claude, Mistral, LLaMA).
- Ability to design vector store architectures and knowledge base integrations.
- Experience translating business needs into technical GenAI architectures.