Building scalable, context-aware AI systems that integrate large language models, RAG pipelines, and advanced data visualization tools for the company
Requirements
- Advanced Python skills and experience with frameworks like MS CoPilot, Make AI agents, Power platform
- Strong knowledge of LLM APIs (e.g., OpenAI, Anthropic, Mistral, Google Gemini)
- Experience with vector databases (e.g. Neo4j, Chroma)
- Familiarity with prompt engineering, embeddings, and semantic search
- Hands-on experience with AI agents or multi-agent orchestration
- Proficient in managing secure APIs and cloud services (AWS/GCP/Azure)
- Experience with Streamlit, D3.js, or React for front-end visualizations
Responsibilities
- Develop AI Systems: Architect and deploy LLM-based applications using RAG pipelines and autonomous agents.
- RAG Workflows: Build end-to-end Retrieval-Augmented Generation pipelines leveraging vector databases (e.g., Pinecone, Weaviate, FAISS).
- Agent-Oriented Architectures: Design multi-agent systems using frameworks like CrewAI, AutoGen, or custom orchestration logic.
- API Integration & Security: Connect to external APIs securely and efficiently; manage tokens and secrets via environmental variables or secure vaults.
- Data Visualization: Use NetworkX, Pyvis, or Neo4j to create vector node models that visualize retrieval results, agent interactions, and system state.
- Collaboration: Partner with data science, product, and DevOps teams to build production-ready applications.
- Documentation & Best Practices: Maintain clean code, internal docs, and contribute to our AI playbook with tools, articles, or even interpretive dances.
Other
- B. A. degree and Certifications preferred.
- Travel may be required for team meetings, Live Quarterly meetings, Workshops, and other events.
- Prolonged periods sitting at a desk and working on a computer.
- Must be able to lift up to 15 pounds at times.
- Full-time position, and hours of work and days are to be determined in conjunction with supervisor.
