Bangalore Traffic Is Broken… Here’s How Rapido Is Fixing It | Ft. Srivatsa Katta, CTO Rapido

2026-03-21 · Source: AIM Network · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Data Science & Analytics · Depth: Intermediate, extended

Summary

Rapido, India's largest ride aggregator, processes approximately 6 million orders daily, with a peak of 6.5 million. The company operates 99% of its technology as self-managed to achieve cost advantages. Rapido utilizes a combination of cloud providers and open-source systems like OpenStreetMap for mapping, overlaying its own data from over three billion lifetime rides to enhance ETA accuracy. Pricing is determined by geographical and marketplace constraints, alongside local regulatory norms, with transparency for both customers and captains. While AI provides insights for surge pricing, operational managers make final decisions. Rapido's engineering team, which is expanding, sees 40-50% of new code generated with AI assistance, boosting productivity by allowing engineers to focus more on systems thinking. The company prioritizes infrastructure resilience through cloud elasticity, Kubernetes, and autonomous autoscaling to handle high demand and seasonal spikes. Safety features include real-time route deviation alerts, emergency calls, and integration with government authorities.

Key takeaway

For VPs of Engineering or Data overseeing large-scale, geographically diverse operations, Rapido's approach highlights the value of investing in self-managed technology and robust data systems. You should prioritize building configurable, platform-based solutions for rapid expansion and leverage AI for developer productivity, while establishing clear guardrails for data privacy. This strategy enables cost efficiency, operational resilience, and the ability to adapt to complex local conditions and regulatory environments.

Key insights

Self-managed tech, data-driven insights, and platform thinking enable Rapido's rapid, cost-effective scaling and operational resilience.

Principles

• Prioritize cost advantage through self-managed technology.
• Combine proprietary data with external sources for enhanced accuracy.
• Automate city expansion with configurable, platform-based systems.

Method

Rapido's ride dispatch system uses geographical queries to find nearest riders, offering transparent ride details and choice to captains. ETA is refined by overlaying proprietary ride data onto map provider information, processed by ML/data systems.

In practice

• Implement AI for code generation to boost engineering productivity.
• Use guardrails for AI tools to ensure data privacy and security.
• Employ Kubernetes and cloud elasticity for infrastructure resilience.

Topics

• Ride-hailing Technology
• AI/ML Optimization
• Tech Scaling
• Geospatial Data
• Shared Mobility

Best for: VP of Engineering/Data, Director of AI/ML, CTO, Software Engineer, Machine Learning Engineer

Related on AIssential

• Operationalizing AI for Scale and Sovereignty — AI factories enable scalable, sustainable, and governed AI by prioritizing data control for secure, tailored solutions.
• Optimizing ML Compute & Orchestration with H2O MLOps | Part 17 — Kubernetes orchestrates AI workloads, enabling resource management, cost optimization, and infrastructure autoscaling.
• AI made your app teams 10x faster. Nobody gave your platform team 10x the headcount. — OpenAI's data platform team manages all core data systems, from analytics to ML infrastructure.
• Abu Dhabi doubles down on French AI with fresh deals — AI's rapid advancement is driving massive infrastructure investments and raising critical safety, ethical, and societal governance challenges.
• Interview: Databricks EMEA CTO on the company’s global expansion in challenging times — Databricks' EMEA CTO highlights strategic expansion and open-source advantage amidst rapid enterprise AI adoption.
• 6 Best AI Context Management Platforms for Fast-Growing SaaS Companies — Effective data context management is critical for scaling SaaS companies and enabling AI initiatives.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by AIM Network.