Mission
Design, build and deploy enterprise-grade AI solutions, autonomous AI agents, and multi-agent orchestration frameworks that support digital transformation initiatives, with a focus on financial services, anti-financial crime processes, and scalable AI platforms. Contribute to the development of secure, reliable, and production-ready AI capabilities that enable organizations to leverage Generative AI and LLM technologies at scale.
Responsibilities:
- Architect and develop production-grade autonomous agents and multi-agent orchestration frameworks (e.g., LangChain, AutoGen, CrewAI).
- Design, build, and deploy AI solutions based on Large Language Models (LLMs) and agentic architectures.
- Guide technical implementations across multiple parallel squads, ensuring consistent and reusable architectural standards.
- Integrate LLMs with external APIs, proprietary tools, databases, and enterprise systems to enable advanced tool-calling capabilities.
- Optimize prompt engineering approaches, context management, state management, and long-running agent workflows.
- Implement monitoring, logging, evaluation, and observability frameworks for AI applications and autonomous agents.
- Apply MLOps/AIOps practices, including model versioning, testing, performance evaluation, and monitoring.
- Design and deploy AI solutions on cloud platforms, primarily AWS, while collaborating on Azure and Databricks environments where applicable.
- Collaborate with business, data science, engineering, and cloud teams to deliver AI-powered solutions in regulated environments.