New opportunity

Lead Software Engineer - Python and AI

JPMorganChase · Bengaluru, India

About this role

As a Lead Software Engineer at JPMorganChase within the Commercial & Investment Bank, Post-Trade Technology team, you are an integral part of an agile team that works to enhance, build, and deliver trusted market-leading technology products in a secure, stable, and scalable way. You will act as a core technical contributor responsible for conducting critical technology solutions across multiple technical areas in support of the firm’s business objectives.

Responsibilities

Designs and builds production-grade agentic AI systems including LLM orchestration layers, RAG pipelines, vector databases, and MCP-based tool integrations.
Develops and reviews secure, high-quality code and debugs solutions written by team members or generated by AI models.
Architects multi-agent and single-agent setups, authors skill files, and writes technical RFCs for new AI capabilities.
Contributes to cloud-native deployments (AWS ECS), CI/CD pipelines, and infrastructure modernisation alongside platform engineering squads.
Builds and iterates on agentic patterns, including multi-hop agents, vector search, and automated code generation, from POC through UAT to full production rollout.
Translates regulatory operations and business requirements into precise technical designs and delivers against quarterly commitments.
Identifies opportunities to automate recurring operational issues, reducing manual toil and improving platform stability.
Participates actively in sprint ceremonies, code reviews, and architecture discussions as a senior technical contributor.
Contributes to an internal developer productivity accelerator as a technical mentor and active builder across 10+ cross-functional teams.
Drives team adoption of enterprise-authorized AI-assisted engineering practices to improve code quality, delivery speed, and operational outcomes.

Required qualifications

Formal training or certification on software engineering concepts and 5+ years of applied experience.
Hands-on practical experience delivering system design, application development, testing, and operational stability.
Advanced proficiency in Python and strong object-oriented programming fundamentals.
Proven experience building and deploying LLM-based or agentic AI systems in production.
Deep understanding of RAG architecture, vector databases, and AI agent frameworks such as LangGraph and MCP.
Proficiency in automation and continuous delivery methods (CI/CD, DevSecOps).
Proficient across all phases of the Software Development Life Cycle with an advanced understanding of agile methodologies and application resiliency patterns.
Practical cloud-native experience on AWS (ECS, Lambda, S3 or equivalent).
Strong analytical and problem-solving skills with the ability to break down complex technical problems independently.
Demonstrated experience leading effective use of approved AI-assisted software development tools and setting team expectations for validating AI outputs.
Strong understanding of responsible AI use in engineering workflows, including data sensitivity, secure handling of inputs/outputs, and adherence to resiliency and security expectations.

Preferred qualifications

Experience with post-trade financial platforms (e.g., Athena, Quartz, SecDB).
In-depth knowledge of financial services industry IT systems, trade reconciliation, and regulatory reporting workflows.
Experience with AI/ML/Vibe coding and agentic development workflows.
Knowledge of distributed computing, data modeling, and performance engineering.
Familiarity with data lineage, data contracts, and data governance frameworks.
Experience with ServiceNow, Jira, or Confluence API integrations.
Regression testing and observability tooling experience in large-scale platforms.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

PythonLLM orchestrationRAGVector databasesAI AgentsLangGraphMCPAWSECSCI/CDDevSecOpsSoftware Development Life CycleAgileObject-oriented programming

Checking your profile…

Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.

Understand the role

What matters most

Production-Grade Agentic AI Development
The role requires designing and deploying LLM orchestration, RAG pipelines, and multi-agent systems from POC to production. You must demonstrate the ability to move beyond experimental AI code to stable, scalable, and secure enterprise-grade implementations.
AI-Assisted Engineering Governance
You are expected to drive the adoption of AI-assisted coding tools across teams while establishing strict validation standards. This involves ensuring that AI-generated code meets security, performance, and compliance requirements, and mentoring others on responsible AI usage.
Cloud-Native Post-Trade System Integration
You must contribute to AWS-based infrastructure and CI/CD pipelines while supporting post-trade financial platforms. Success requires balancing modern cloud-native practices with the specific stability and regulatory needs of financial services.

Likely challenges to think through

Balancing AI Innovation with Financial Security
Integrating agentic AI into highly regulated post-trade environments creates a tension between rapid development and strict data sensitivity/security protocols. Prepare by articulating how you implement 'human-in-the-loop' validation and secure data handling within AI workflows.
Managing Non-Deterministic AI Outputs
Agentic systems can produce variable results, which is difficult to reconcile with the high reliability required for financial systems. Prepare by discussing your strategies for observability, regression testing, and robust error handling in LLM-based applications.
Cross-Functional Technical Leadership
As a mentor across 10+ teams, you will face the challenge of standardizing AI practices across diverse technical groups. Prepare by highlighting your experience in writing technical RFCs and influencing engineering culture through clear documentation and collaborative architecture discussions.

Practice your answers

Technical practice

Designing Production-Grade Agentic AI Systems

What to coverExplain your approach to architecting multi-agent systems, specifically how you handle LLM orchestration and tool integration using frameworks like LangGraph or MCP. Focus on how you ensure reliability, state management, and error handling when moving from a proof-of-concept to a production environment.

RAG Pipeline Optimization and Vector Databases

What to coverDescribe the trade-offs you consider when selecting a vector database and designing a RAG pipeline for financial data. Discuss how you manage data retrieval accuracy, handle context window limitations, and ensure data lineage and governance within the pipeline.

Validating AI-Generated Code and Outputs

What to coverAs a lead, how do you establish validation standards for code or technical solutions generated by AI models? Address how you balance the speed of AI-assisted development with the necessity for secure, high-quality code and rigorous peer review.

Cloud-Native Deployments on AWS

What to coverDiscuss your experience deploying Python-based applications using AWS ECS and Lambda. Explain how you integrate these services into a CI/CD pipeline while maintaining operational stability and security in a regulated environment.

Application Resiliency and Performance Engineering

What to coverHow do you approach performance engineering and resiliency for large-scale distributed systems? Suggestion: Prepare to discuss specific patterns you use to handle failures, such as circuit breakers or retries, and how you utilize observability tools to monitor system health.

Automating Operational Toil

What to coverProvide an example of how you have identified and automated recurring operational issues within a software development lifecycle. Explain the metrics you used to measure the success of the automation in terms of platform stability and developer productivity.

Responsible AI in Engineering Workflows

What to coverHow do you address data sensitivity and security when integrating AI tools into engineering workflows? Explain your process for ensuring that inputs and outputs remain compliant with enterprise security expectations and data governance frameworks.

Object-Oriented Design in Python

What to coverGiven the requirement for advanced Python proficiency, explain how you apply object-oriented principles to build scalable and maintainable AI systems. Discuss how you structure your code to facilitate modularity and reuse across cross-functional teams.

Behavioural practice

Mentoring and Technical Leadership

What to coverDescribe a situation where you acted as a technical mentor for multiple cross-functional teams. Focus on how you influenced their adoption of new engineering practices or tools while balancing your own delivery commitments.

Translating Business Requirements to Technical Design

What to coverShare an experience where you had to translate complex regulatory or business requirements into a precise technical design. Explain how you ensured the final delivery met the business objectives while adhering to technical constraints.

Managing Conflict in Architecture Discussions

What to coverDescribe a time you participated in a high-stakes architecture discussion where there was disagreement on the technical approach. How did you advocate for your design while ensuring the team reached a consensus that supported the firm's objectives?

Driving Team Adoption of New Practices

What to coverProvide an example of how you drove the adoption of a new technology or AI-assisted practice within your team. Detail the steps you took to set expectations, address resistance, and measure the impact on delivery speed and code quality.

Sharpen your knowledge

Topics to prepare

Agentic AI Architecture
Focus on the design patterns for multi-agent systems, including LLM orchestration, state management, and tool integration via MCP. Exercise: Draft a technical RFC for a hypothetical multi-agent system that automates a post-trade reconciliation task, detailing how agents interact and handle tool-use failures.
Responsible AI in Engineering
Understand the security and compliance requirements for deploying AI in a regulated financial environment. Exercise: Create a checklist for validating AI-generated code, focusing on data sensitivity, secure input/output handling, and resiliency against hallucinations or prompt injection.

Skills to revise

Python Agent Frameworks
Develop proficiency in building production-grade agents using LangGraph or similar frameworks. Exercise: Build a small-scale Python application using LangGraph that implements a multi-hop reasoning chain to retrieve and process data from a mock vector database.
AWS Cloud-Native Deployment
Master the deployment of containerized AI applications on AWS ECS. Exercise: Create a CI/CD pipeline configuration that deploys a Python-based AI service to AWS ECS, incorporating automated testing and security scanning steps.
RAG Pipeline Optimization
Refine the ability to build and iterate on Retrieval-Augmented Generation pipelines. Exercise: Implement a RAG pipeline using a vector database, focusing on optimizing retrieval accuracy through chunking strategies and metadata filtering.

Your preparation checklist

Prepare a technical project walkthrough of an agentic AI system
Develop a concise presentation of a production-grade AI project you have led. Focus on your architecture choices regarding RAG pipelines, vector database selection, and agent orchestration frameworks like LangGraph or MCP. Be prepared to explain how you managed multi-hop agent logic and ensured system reliability.
Draft a technical RFC for an AI-driven automation solution
Create a sample Request for Comments (RFC) document that outlines a proposed solution for an operational challenge. Include sections on technical design, cloud-native deployment strategy on AWS (ECS/Lambda), and how you would integrate AI-assisted development tools while maintaining security and data sensitivity standards.
Define your framework for responsible AI engineering
Prepare to discuss your approach to validating AI-generated code and outputs. Articulate how you establish team-wide standards for secure coding, peer review, and automated testing when using AI tools, specifically addressing how you handle data lineage and sensitivity in a regulated financial environment.
Map your experience to post-trade financial workflows
Review your background in financial services to identify specific examples of trade reconciliation, regulatory reporting, or distributed computing projects. Prepare to explain how your technical designs have improved platform stability or reduced manual toil in large-scale, high-stakes environments.
Formulate targeted questions for the interviewers
Prepare questions that demonstrate your seniority, such as: How does the team balance rapid AI experimentation with the strict resiliency requirements of post-trade systems? What are the current challenges in scaling agentic patterns across the 10+ cross-functional teams you support?

Availability has not yet been verified. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in India. Matched to this role, not your profile.

Explore more jobs

Finding similar opportunities…