• Build RAG systems: Architect, prototype, and deploy RAG pipelines, combining vector search, hybrid retrieval, reranking and contextual compression techniques.
• Build LLM powered agent systems : Contribute to design and orchestration of multi-agent LLM systems using community frameworks and custom orchestration layers.
• Solve complex problems : Work on a variety of information extraction, information storage and information retrieval problems for both structured and unstructured data.
• Collaborate cross-functionally : Partner with cross-functional (product, infra, data engineering, and software engineering) to build robust, high-scale systems that underlie all of our data processing and ML Operations.
Don’t meet every single requirement? Studies have shown that women and people of color are less likely to apply to jobs unless they meet every qualification. At Affinity, we are dedicated to building a diverse, inclusive, and authentic workplace, so if you’re excited about this role, but your past experience doesn’t perfectly align with the qualifications above, we encourage you to apply anyways. You may be just the right candidate for this or other roles.
• Experience with enterprise AI applications with strict compliance, audit, or legal requirements
• Experience with dataset engineering, including data curation, augmentation, and synthesis, to assist ML model improvements.
• Experience with multi-modal search
• Experience with graph based recommendation systems, such as graph NN.
• Experience with developing AI applications powered by agent-based systems
• Experience with packaging, CI/CD and pipeline automation.
Tech stack : Our ML pipeline manages multiple Python services that support various AI features, including utilizing OCR to extract information from unstructured data, serving embedding models to vectorize chunks, and ranking a list of recommendations based on relevance and user preference.