About the position
CAIS is the pioneer in democratizing access to and education about alternative investments for independent financial advisors, empowering them to engage and transact with leading asset managers on a massive scale through a wide variety of alternative investment products and technology solutions. CAIS provides financial advisors with a broad selection of alternative investment strategies, including hedge funds, private equity, private credit, real estate, digital assets, and structured notes. CAIS also delivers industry-leading technology, operational efficiency, and world-class client service throughout the pre-trade, trade, and post-trade experience. CAIS supports over 50,000 advisors who oversee more than $6 trillion in network assets. As a Software Engineer focused on Search and Retrieval-Augmented Generation (RAG), you will play a pivotal role in redefining how financial professionals discover, analyze, and engage with alternative investments. Your work will directly influence product vision, drive core framework development, and create scalable AI solutions that will be adopted across the CAIS ecosystem.
Responsibilities
- Develop advanced RAG pipelines to seamlessly integrate and analyze structured and unstructured data.
- Design and develop algorithms to strategically prompt LLMs for complex, agentic RAG workflows and chains.
- Fine tune RAG pipeline for accuracy, completeness and contextual relevance.
- Write high-quality, modular code to capture agentic design patterns, ensuring reusability and maintainability.
- Rapidly prototype features for user demonstrations and feedback loops.
- Build systems to evaluate AI agents, leveraging both custom-built solutions and third-party vendor products.
- Create comprehensive, carefully crafted end-to-end and unit test-cases for agents and related sub-components to ensure system robustness.
- Prepare and optimize structured and unstructured data for RAG processes, enhancing performance and reliability.
- Deploy RAG pipelines on cloud platforms with a focus on low latency and high scalability.
- Stay ahead of the curve in Generative AI research, continuously adapting to new techniques and tools for optimal LLM use.
Requirements
- Strong Python programming experience, with a deep understanding of data structures and algorithms.
- Expertise in retrieval augmented generation (RAG), including chunking strategies, hybrid indexing, graph RAG, and agentic RAG.
- Hands-on experience fine-tuning search and/or RAG systems using ElasticSearch, Weaviate or similar hybrid search products.
- Proficiency in prompt engineering with an intuitive grasp of LLM behaviour and patterns such as ReACT, CoT, function calling and routing.
- Familiarity with open-source frameworks such as LangChain and LlamaIndex.
- Experience in Generative AI/LLM testing, validation, and performance evaluation.
- Strong understanding of cloud deployment technologies, including Kubernetes, Docker and/or cloud ML platforms such as Amazon bedrock.
- Exceptional attention to code quality, with a focus on adhering to established software design patterns and best practices.
- 4+ years of experience in information retrieval and search relevance in a production system.
- Experience in related SaaS product development is a huge plus.
- BS in Computer Science or a related field.
- 4 years of professional experience in a workplace setting.
Benefits
- Market competitive salary
- Performance bonus
- Generously subsidized healthcare with 100% employer paid dental and vision insurance
- Employer matched retirement plan
- Wellness programs
- Generous PTO and parental leave
- Flexible, hybrid in-office model
