Agentic Design Lead - RAG & LangGraph

Role Overview :

As an Agentic Design Lead, you will spearhead the architecture and implementation of autonomous AI systems that redefine how businesses interact with data. You will bridge the gap between high-level product requirements and technical execution, working closely with cross-functional engineering and product teams to design agentic workflows that are reliable, scalable, and secure. Your work will directly influence the efficiency of our clients' operations, transforming how they leverage Large Language Models to solve real-world, multi-step problems.

Key Responsibilities :

- Design and optimize Retrieval Augmented Generation (RAG) pipelines to ensure high-fidelity, context-aware responses in mission-critical applications.

- Lead the technical strategy for deploying AI agents across cloud environments, ensuring seamless integration with existing enterprise infrastructure.

- Evaluate and fine-tune Large Language Models to improve task-specific performance and reduce latency in production environments.

- Mentor engineering teams on best practices for agentic design, fostering a culture of technical rigor and continuous improvement.

- Collaborate with stakeholders to translate ambiguous business requirements into robust, automated AI workflows that drive measurable business outcomes.

Required Skillset :

- Proficiency in orchestrating AI workflows using Langgraph and managing the lifecycle of Large Language Models.

- Hands-on experience architecting scalable solutions on major cloud platforms including AWS, GCP, or Azure.

- Strong ability to communicate complex technical concepts to non-technical stakeholders and lead cross-functional initiatives effectively.

- Proven track record of solving high-complexity problems with 8 - 12 years of professional experience in software engineering or AI research.

- Ability to thrive in a fast-paced, hybrid work environment, balancing independent technical contribution with team leadership responsibilities.

- A degree in Computer Science, Engineering, or a related quantitative field is preferred, complemented by a deep curiosity for emerging AI research.