AI Architecture & System Design :

o Architect, prototype, and deploy large language model (LLM) and retrieval-augmented generation (RAG) systems that enhance Supplier.io products.

o Design scalable architectures for integrating LLMs into production workflows-balancing cost, latency, and performance.

o Develop agentic AI workflows to automate complex tasks such as supplier search, enrichment, classification, and insights generation.

Collaboration & Leadership :

o Partner closely with AI Engineers to define implementation details, guide development, and ensure code quality and performance.

o Collaborate with Product Managers and the CTO to translate business objectives into robust AI technical solutions.

o Establish best practices for model orchestration, evaluation, and continuous improvement.

Research & Innovation :

o Explore emerging frameworks (LangChain, LlamaIndex, CrewAI, AutoGen, etc.) and assess their applicability to Supplier.io use cases.

o Prototype, benchmark, and refine LLM-driven components for semantic search, summarization, supplier matching, and recommendation systems.

o Drive experimentation to evaluate open-source and proprietary LLMs, embeddings, and vector databases (e.g., Pinecone, Chroma, Weaviate).

Operational Excellence :

o Define observability, testing, and deployment standards for AI components across environments.

o Work with DevOps and Data Engineering to optimize pipelines for scalability and cost efficiency.

o Contribute to model governance, documentation, and reproducibility practices.

Security, Privacy & Compliance :

o Ensure all LLM and RAG implementations follow security best practices related to data confidentiality, PII handling, and prompt injection prevention.

o Partner with Legal/Security to ensure compliance with SOC 2, GDPR, and other relevant standards.

AI Roadmap & Strategy Contribution :

o Contribute to the annual AI roadmap by proposing scalable LLM-powered features, tools, and platform investments.

o Evaluate build-vs-buy decisions for vendor AI tools and foundational models.

What You Will Bring :

- 7+ years of experience in AI/ML engineering, with 3+ years of recent focus on LLM, NLP, or RAG-based architectures.

- Proven experience designing and deploying AI systems in production using frameworks like LangChain, LlamaIndex, Hugging Face, or Ray.

- Strong understanding of LLM architecture, embeddings, fine-tuning, and inference optimization.

- Proficiency in Python and modern ML frameworks (PyTorch, TensorFlow, scikit-learn).

- Experience with vector databases (Pinecone, Chroma, FAISS, Weaviate) and cloud platforms (GCP, AWS, or Azure).

- Familiarity with agentic AI frameworks and multi-agent orchestration concepts.

- Working knowledge of MLOps, model evaluation, and continuous delivery pipelines.

- Excellent collaboration and communication skills with the ability to influence technical direction across teams.