3 months ago
Remote, United StatesSenior / Staff+
Responsibilities
- Design, implement, and optimize LLM-powered systems.
- Build and manage data indexing and retrieval pipelines.
- Implement and maintain vector databases.
- Integrate open-source and proprietary LLMs into the CoreStory Platform.
- Develop and refine AI-driven features.
- Collaborate with DevOps and backend teams to deploy scalable AI services.
- Continuously benchmark model performance, latency, and cost.
- Stay current with advancements in AI and propose innovative applications.
- Contribute to internal documentation and evaluation methodologies.
Requirements
- 7+ years of overall engineering experience with at least 3+ years in AI engineering or applied NLP.
- Strong hands-on experience with LlamaIndex, LangChain, or similar frameworks.
- Experience designing and implementing vector database solutions.
- Solid understanding of LLM APIs.
- Proficiency in Python and experience with libraries like FastAPI, Pandas, or NumPy.
- Understanding of retrieval-augmented generation patterns and tokenization.
- Familiarity with prompt engineering and chat agent architectures.
- Strong problem-solving and analytical mindset.
- Demonstrated interest in the evolving AI landscape.
Benefits
- Competitive compensation and equity.
- Flexible, remote-first work environment.
- Opportunities to define and build the AI roadmap.
- Collaborative, learning-oriented culture.
- Access to cutting-edge AI models, research, and infrastructure.