About the Role 

Most Important

• Proven experience architecting and deploying production-ready AI agents and RAG pipelines using orchestration frameworks like LangChain or LlamaIndex.

• Deep understanding of the Model Context Protocol (MCP) or similar integration standards for connecting AI models to external financial or business tools.

• Proficiency with local inference and model serving tools such as Ollama, vLLM, or Hugging Face Transformers.

• Strong backend proficiency for building high-performance, fault-tolerant AI services.

• Experience implementing and managing vector search solutions using Supabase, pgvector, or dedicated databases like Pinecone.

Nice to Have

• Experience using AI engineering platforms like LangSmith, Arize, or Weights & Biases for observability and evaluation.

• Familiarity with rapid prototyping tools for AI interfaces such as Streamlit, Gradio, or the Vercel AI SDK.

• Active contributions to open-source AI ecosystems or maintenance of developer tools.

• Hands-on experience with data manipulation and scientific computing using Pandas, NumPy, and Scikit-learn.

• Expertise in implementing RAG pipelines with vector databases like Pinecone, Milvus, Weaviate, or ChromaDB.

• Experience building agentic workflows using  LangGraph, AutoGen, or CrewAI.

Personal Traits

• Proactive Communicator: You value clear, asynchronous communication and keep stakeholders aligned across time zones.

• Ownership Mindset: You take pride in your work, owning features from conception to deployment and maintenance.

• Continuous Learner: You have an insatiable curiosity for new tools and emerging architectural patterns.