Senior AI Engineer in Harwell

My client is seeking a full‐stack AI/ML engineer with deep expertise in agentic AI frameworks such as LangGraph (or equivalent) and proven commercial experience building complex, multi‐agent systems with at least four agents. This role blends cutting‐edge AI research with hands‐on deployment leadership. You will design and optimise agent‐based AI pipelines, deploy them into cloud and edge environments, and own the infrastructure that keeps them secure, scalable, and cost‐efficient. You will be as comfortable in a Jupyter Notebook as you are in a Terraform config, turning research ideas into production systems that run reliably in constrained environments.

Key Responsibilities

• Architect, build, and optimise multi‐agent AI systems using LangGraph or similar frameworks.
• Integrate LLMs into agent workflows for search, reasoning, and automation at scale.
• Conduct applied research in LLMs, NLP, and agent orchestration, focusing on edge and offline deployments.
• Build production‐ready ML pipelines from ingestion to inference.

Infrastructure & Deployment

• Implement and maintain multi‐account, multi‐region AWS environments using IaC (Terraform, Helm, CloudFormation).
• Manage Kubernetes clusters (EKS/OpenShift), service meshes, and container registries.
• Implement GitHub Actions / Argo CD pipelines for automated, zero‐touch deployments.
• Lead security hardening efforts using GuardDuty, CloudWatch, IAM best practices.
• Set up observability stacks for proactive monitoring and performance tuning.
• Own backup and disaster recovery for services you've created.

Cross‐Functional & Process

• Collaborate closely with other engineers, product managers, and CTO.
• Mentor engineers on agentic AI design best practices.
• Present technical findings and research outcomes to technical and non‐technical stakeholders.

You will be working at the intersection of advanced AI research and real‐world infrastructure, shaping how my client brings agentic AI systems to production in challenging environments. If you thrive on building multi‐agent systems, deploying them securely at scale, and experimenting with new ways to run AI at the edge, you'll find both the technical depth and creative freedom you're looking for here.

Required Skills & Experience

• MOD Security Clearance (or ability to obtain).
• Commercial experience delivering LangGraph or equivalent agentic AI projects with more than four agents in production.
• Strong grasp of multi‐agent orchestration, memory, and tool integration.
• Proficiency in Python for AI development and Bash/Go for automation.
• Familiarity with AWS core services (EC2, VPC, IAM, S3, ALB/ELB, CloudFront, ECR/ECS, Elastic Beanstalk, Control Tower).
• Familiarity with IaC (Terraform, Terraform Cloud, CloudFormation) and expertise in containerisation (Docker, Docker Compose).
• Solid CI/CD engineering with GitHub Actions and/or Argo CD.

Preferred / Bonus

• Research experience in edge AI or constrained/offline deployments.
• MLOps experience (SageMaker, Kubeflow, ZenML).
• Experience building RESTful services around AI pipelines.
• ISO 27001, NIST SSDF, OWASP SAMM, or GDPR compliance literacy.
• Experience with AWS Karpenter, Prometheus, or similar observability stacks.

Soft Skills

• Research‐driven mindset, eager to experiment and iterate.
• Ability to bridge the gap between cutting‐edge AI research and practical deployment.
• Strong communicator with the ability to mentor and influence across teams.
• Comfortable owning projects from concept through production deployment.

Benefits Include

• Rapid career progression and personal growth.
• Opportunity to shape the future of a fast‐growing, successful, early‐stage business.
• Flexible working hours.
• Hybrid working model.

My client is committed to creating an inclusive team experience for all. Regardless of race, gender, religion, sexual orientation, age, disability, or parental status, we believe our work is at its best when everyone feels free to be their authentic self.