Lead AI Engineer – Vice President, -Software Engineer

Overview

Build scalable, high-performance enterprise applications as a Java Backend Engineer on the Institutional Securities Technology team supporting Prime Brokerage and Institutional Equity. The role focuses on deep Java and Spring Boot backend engineering while adopting agentic AI workflows.

What you'll do

• Develop software using Java.
• Build scalable, high-performance enterprise applications.
• Develop and maintain software solutions that support business needs.
• Use Spring Boot, microservices, REST APIs, and messaging integrations including Kafka, JMS, and RabbitMQ.
• Apply SQL, concurrency, and distributed systems design.
• Work with CI/CD, DevOps, and production observability.
• Improve application performance and scalability.
• Apply strong problem-solving skills and learn new technologies quickly.
• Use AI-assisted and agentic software development approaches.
• Integrate LLMs into backend systems using OpenAI, Azure OpenAI, Anthropic, or equivalent technologies.
• Design multi-agent workflows using orchestrator/subagent patterns, agent-to-agent communication, and guardrails for autonomous systems.
• Address AI system reliability concerns including hallucination mitigation, tracing agent runs, latency, and cost management.
• Experiment with emerging agentic patterns including ReAct, Chain-of-Thought, reflection loops, and human-in-the-loop gates.
• Apply RAG architecture and vector database concepts.

What you'll need

• 6+ years hands-on Java development.
• Deep Spring Boot, microservices, REST APIs, and messaging integrations experience with Kafka, JMS, and RabbitMQ.
• Strong SQL, concurrency, and distributed systems design skills.
• CI/CD, DevOps, and production observability experience.
• Experience in performance tuning and scalability improvements.
• Demonstrated strong problem-solving ability and comfort learning new technologies quickly.
• Genuine interest in AI-assisted or agentic software development.
• Basic hands-on exposure through personal projects, POCs, or production to LLM-integrated systems, such as calling OpenAI, Azure OpenAI, or Anthropic APIs, or using GitHub Copilot or Claude Code in a substantial way.
• Ability to grasp and reason about orchestrator/subagent patterns, tool/function calling, eval-driven iteration ("hill climbing"), and basic prompt engineering.
• Python exposure for AI integration, scripting, or data pipeline use cases.
• Hands-on experience integrating LLMs into production backend systems using OpenAI, Azure OpenAI, Anthropic, or equivalent.
• Working knowledge of agentic AI frameworks including LangChain, LangGraph, Spring AI, AutoGen, CrewAI, or Claude Agent SDK, including agent memory, tool calling, and multi-step reasoning loops.
• Ability to design multi-agent workflows with orchestrator/subagent patterns, agent-to-agent communication, and guardrails for autonomous systems.
• Awareness of AI system reliability concerns including hallucination mitigation, observability through tracing agent runs, latency, and cost management.
• Curiosity and self-driven experimentation with emerging agentic patterns including ReAct, Chain-of-Thought, reflection loops, and human-in-the-loop gates.
• RAG architecture and vector database concepts.
• Financial Services or Investment Banking domain experience.

Details

• Location: Mumbai, India.