Principal Software Engineer - Data and AI - Accelerator Business

JPMorgan Chase & Co.; Greater London; On-site; GBP 120,000 - 180,000; Full time

Job summary

JPMorgan Chase & Co. in London is seeking a Principal Software Engineer - Applied AI ML Director to drive GenAI initiatives, designing scalable documentation, SDKs, and pipelines for rapid AI deployment.

You will mentor squads, shape platform design, and advance model integration across cloud-native microservices while focusing on reliability and governance.

Qualifications

• Proficiency in Java and/or Python programming languages.
• Deployed production systems to GenAI platforms such as Google VertexAI, OpenAI, AWS Bedrock, or LangChain.
• Utilized cloud technologies (AWS/Azure/GCP), distributed systems, CI/CD tools, infrastructure-as-code tools, and containerization/orchestration tools (Docker, Kubernetes).
• Previous experience deploying and managing LLM-model based applications and agents.
• Exposure to vector stores such as Pinecone, GCP RAG engine, and AWS S3 Vector Buckets.
• Exposure to cloud-native microservices architecture.
• Familiarity with Retrieval-Augmented Generation (RAG), agentic system architectures, and Model Context Protocol (MCP).
• Hands-on experience with agentic frameworks (LangChain, CrewAI, AutoGen, LangGraph, ADK).
• Strong communication skills for both technical and non-technical audiences.

Responsibilities

• Design and develop scalable, self-service solutions for documentation, SDKs, configurations and pipelines to enable rapid deployment of GenAI applications (including Retrieval-Augmented Generation pipelines) and agents with planning, memory, and workflow orchestration.
• Implement tools and frameworks for model versioning, experiment tracking, and lifecycle management
• Develop systems to monitor model performance and address data and model drift
• Recommend best practices for model integration and deployment patterns
• Design and implement effective testing strategies, including unit, component, integration, end-to-end, performance, and champion/challenger tests, establish output validation best practices, recommendations and guardrails to reduce hallucinations.
• Ensure platform compliance with data privacy, security, and regulatory standards
• Mentor team members on platform design principles and best practices
• Guide colleagues on coding practices, design principles, and implementation patterns for high-quality, maintainable solutions
• Deploy scalable AI services to cloud infrastructure, ensuring monitoring, and observability for agent performance.
• Design microservices-based architectures and orchestrate multi-step workflows; instrument agents for tracing, metrics, and feedback loops to continuously improve reliability and utility.

Skills

Java

Python

Strong communication

Tools

LangChain

CrewAI

AutoGen

LangGraph

ADK

Docker

Kubernetes

Google VertexAI

OpenAI

AWS Bedrock

Pinecone

AWS S3 Vector Buckets

Job description

Out of the successful launch of Chase in 2021, we’re a new team, with a new mission. We’re creating products that solve real world problems and put customers at the center - all in an environment that nurtures skills and helps you realize your potential. Our team is key to our success. We’re people-first. We value collaboration, curiosity and commitment.

As a Principal Software Engineer - Applied AI ML Director at JPMorganChase within the Accelerator Business, you are the heart of this venture, focused on getting smart ideas into the hands of our customers. You have a curious mindset, thrive in collaborative squads, and are passionate about new technology. By your nature, you are also solution-oriented, commercially savvy and have a head for fintech. You thrive in working in tribes and squads that focus on specific products and projects – and depending on your strengths and interests, you'll have the opportunity to move between them.

While we’re looking for professional skills, culture is just as important to us. We understand that everyone's unique – and that diversity of thought, experience and background is what makes a good team, great. By bringing people with different points of view together, we can represent everyone and truly reflect the communities we serve. This way, there's scope for you to make a huge difference – on us as a company, and on our clients and business partners around the world.

Job Responsibilities

• Design and develop scalable, self-service solutions for documentation, SDKs, configurations and pipelines to enable rapid deployment of GenAI applications (includingRetrieval-Augmented Generation (RAG) pipelines) and agents withplanning, memory, and workflow orchestration
• Implement tools and frameworks for model versioning, experiment tracking, and lifecycle management
• Develop systems to monitor model performance and address data and model drift
• Recommend best practices for model integration and deployment patterns
• Design and implement effective testing strategies, including unit, component, integration, end-to-end, performance, and champion/challenger tests, establishoutput validation best practices, recommendations and guardrails to reduce hallucinations.
• Ensure platform compliance with data privacy, security, and regulatory standards
• Mentor team members on platform design principles and best practices
• Guide colleagues on coding practices, design principles, and implementation patterns for high-quality, maintainable solutions
• Deploy scalable AI services to cloud infrastructure, ensuring monitoring, and observability for agent performance.
• Design microservices-based architectures and orchestrate multi-step workflows; instrument agents for tracing, metrics, and feedback loops to continuously improve reliability and utility.

Required qualifications, capabilities and skills:

• Demonstrate proficiency in Java and/or Python programming languages
• Deployed production systems to GenAI platforms such as Google VertexAI, OpenAI, AWS Bedrock, or LangChain
• Utilized cloud technologies (AWS/Azure/GCP), distributed systems, CI/CD tools, infrastructure-as-code tools, and containerization/orchestration tools (Docker, Kubernetes) to operate, support, and secure mission-critical applications
• Previous experience deploying and managingLLM-model basedapplications and agents
• Exposure to vector stores such as Pinecone, GCP RAG engine, and AWS S3 Vector Buckets
• Exposure to cloud-native microservices architecture
• Familiarity with advanced AI/ML concepts and protocols, including Retrieval-Augmented Generation (RAG), agentic system architectures, and Model Context Protocol (MCP)
• Hands-on experience with agentic frameworks (LangChain, CrewAI, AutoGen, LangGraph, ADK).
• Strong communication skills for both technical and non-technical audiences.

Preferred qualifications, capabilities and skills:

• Experience working in highly regulated environments or industries
• Experience with distributed computing, data sharding, and performance optimization.
• Demonstrated experience in financial services, particularly retail banking operations.