Company Overview
Crisil Integral IQ, owned by S&P Global, support the execution of its clients’ financial analysis workflows, providing offshore analysts and tools. It serves a significant portion of the financial industry, including 15 of the top 20 global investment banks and 35 of the top 50 commercial banks.
Project Details
Generative AI will fundamentally impact on the day-to-day job of financial analysts, automating certain tasks, and enabling much deeper analysis at a larger scale. In the context of this transformation, Crisil Integral IQ is developing tools and solutions for integrating GenAI into several financial analysis workflows. The solutions are developed and tested in partnership with large asset managers and banks. These solutions combine our in-depth knowledge with agentic architectures, leveraging the capabilities of frontier LLMs. To support this effort, we are currently recruiting an international team that will be focused on prototyping and experimentation using the latest innovations and tools in the field of agentic systems.
Role Overview
We're seeking an experienced Backend Developer with expertise in GenAI systems to join our innovative team. In this role, you will be responsible for developing enterprise-grade, distributed back-end systems with a focus on GenAI system architecture and database design.
Responsibilities
- Design and implement production-grade RAG pipelines
- Develop scalable vector storage solutions
- Create sophisticated caching and token optimization strategies
- Implement AI security monitoring and compliance tools
- Design and maintain complex database architectures
- Develop secure, high-performance APIs for large-scale systems
- Implement advanced architectural patterns for distributed systems
- Create streaming LLM response handlers and vector search APIs
- Design efficient vector update and maintenance strategies
- Develop prompt injection prevention systems
- Create and optimize CI/CD pipelines and DevOps workflows
Required Qualifications
- Awareness and hands-on experience with LLM-based applications
- 5+ years of experience building enterprise-grade, distributed back-end systems
- Master's degree in Computer Science
- Expertise in microservices architecture and event-driven systems
- Strong background in designing for scalability and fault tolerance
- Expert proficiency in server-side languages (Python, Java, Go)
- Advanced knowledge of cloud platforms (AWS, Azure, GCP)
- Expertise in GenAI architectures (RAG systems, vector search, prompt engineering)
- Experience with vector databases and embedding technologies
- Knowledge of AI governance, security and cost optimization
Nice to have
- Active contributor to GenAI community (publications, contributions to open-source projects, blog, personal GenAI projects, etc.)
- Additional certifications in back-end development or cloud computing
- Advanced certification in LLM development and deployment
- Proven track record of implementing production-grade RAG systems
- Experience contributing to large-scale, distributed applications
- Experience with model servers (vLLM, Text Generation Inference)
Interested candidates who meet the qualifications are encouraged to apply. If you do not meet all the qualifications but you think you can still be a good match, don’t hesitate to apply.