Lead GenAI & Agentic AI Engineer

JP Morgan Chase; Glasgow; On-site; GBP 62,000 - 102,000; Full time

Job summary

J.P. Morgan is seeking an experienced AI engineer to design, develop, and deploy GenAI and agentic AI solutions across business workflows.

You will build LLM-powered applications, including RAG-based pipelines, copilots, and tool-using agents, with production-grade Java/Python services and secure, scalable architectures. Responsibilities include developing prompt strategies, data pipelines, and ML lifecycle practices with CI/CD, testing, and observability.

Qualifications

• Undergrad or Masters degree, or equivalent practical experience, in Computer Science, Data Science, Machine Learning, or a related field.
• Hands-on experience building applied AI/ML or GenAI solutions such as RAG, classification, extraction, ranking, summarization, and copilots.
• Familiarity with MCP (Model Context Protocol), Agent Skills, and architectures that connect models to tools and data through standardized interfaces.
• Familiarity with LLM application patterns including embeddings/vector search, prompt orchestration, tool calling/function calling, safety/guardrails, and evaluation.
• Strong software engineering experience delivering production systems, with the ability to design maintainable architectures and write clean, testable code.
• Proficiency in Java and/or Python and experience building APIs/services and integrating with data sources and downstream systems.
• Experience deploying solutions on AWS and cloud-native environments, with understanding of security fundamentals and operational excellence.
• Experience with CI/CD, code reviews, unit testing, and deployment automation.
• Experience with containers and orchestration such as Docker and Kubernetes/EKS, along with production monitoring practices.
• Experience building agentic AI systems, including multi-step workflows, tool routing, planning, memory patterns, and supervision/fallback strategies.
• Experience with AWS Bedrock and/or SageMaker, or equivalent managed ML/GenAI platforms, and deployment patterns for scalable inference.
• Experience with evaluation frameworks and approaches such as golden datasets, LLM-as-judge, human-in-the-loop review, and red teaming.
• Experience fine-tuning models such as LoRA, QLoRA, or DoRA, and/or working with SLMs, embeddings, and retrieval systems.
• Experience with developer productivity tooling such as GitHub Copilot and Claude Code, paired with strong SDLC controls.
• Knowledge of the financial services industry and operating in regulated environments, including auditability, controls, and data handling.
• Exposure to distributed compute/training concepts such as DDP and sharding, and performance/cost optimization.

Responsibilities

• Design, develop, and deploy GenAI and Agentic AI solutions that improve automation, decision-making, and user experience across business workflows.
• Build LLM/SLM-powered applications including RAG-based systems, summarization/extraction pipelines, chat/copilot experiences, and tool-using agents.
• Engineer production-grade services using Java and/or Python, including REST/gRPC APIs, microservices, and libraries, following secure coding and reliability best practices.
• Develop prompt strategies and prompt engineering assets such as templates, routing, and guardrails, and implement automated evaluation to improve quality over time.
• Build and maintain data pipelines and processing workflows required for ML/GenAI use cases using cloud services.
• Apply MLOps practices across the lifecycle, including experimentation, versioning, CI/CD, deployment, monitoring, and maintenance for models, prompts, and agents.
• Implement robust testing, including unit and integration testing, performance benchmarking for latency and cost, and observability through logging, metrics, and tracing for AI services.
• Collaborate with cross-functional stakeholders to define requirements, success metrics, and rollout plans, and communicate complex topics clearly to technical and non-technical audiences.
• Work effectively in ambiguous environments with multiple stakeholders and strong problem-solving focus.

Skills

GenAI engineering

Java/Python

AWS

CI/CD

MLOps

LLM patterns

Software architecture

Safety/guardrails

Problem solving

Education

Undergrad or Masters in CS/Data Science/ML

Tools

Docker

Kubernetes/EKS

REST/gRPC

GitHub Copilot

Claude Code

Job description

J.P. Morgan is seeking an experienced AI engineer to design, develop, and deploy GenAI and agentic AI solutions across business workflows.

You will build LLM-powered applications, including RAG-based pipelines, copilots, and tool-using agents, with production-grade Java/Python services and secure, scalable architectures. Responsibilities include developing prompt strategies, data pipelines, and ML lifecycle practices with CI/CD, testing, and observability.