You will lead the technical direction for advanced agentic AI and model fine-tuning initiatives.
Responsibilities
- Guide the team in reinforcement learning and resolve complex technical issues during the fine-tuning process.
- Architect advanced multi-step RAG systems incorporating self-reflection, grading, cross-encoders, and bi-encoders.
- Design and implement agentic AI solutions, including tool architecture and MCP servers.
- Benchmark performance for both fine-tuned models and RAG-based implementations.
- Develop sophisticated RAG pipelines that move beyond naive implementations.
Required Skills
- 5+ years of experience in Deep Learning training.
- Expertise in Agentic AI and multi-step RAG architectures.
- Proven ability to fine-tune models, particularly in non-standard architectures.
- Experience building and writing advanced RAG code and pipelines.
- Proficiency in architecting tools and MCP servers.
- Strong ability to articulate technical solutions and guide engineering teams.
- Degree in any field.
Preferred Skills
- Prior experience with LLM fine-tuning.