deploy LangGraph-based agentic systems that orchestrate LLM-driven tools and workflows. · Build and integrate modular AI agents capable of real-world task execution in cloud-native environments. · Utilize AWS services such as Lambda, StepFunctions, Bedrock, S3, ECS/Fargate, DynamoDB, and API Gateway to support scalable, serverless infrastructure. · Write production-grade Python code, following best … or LLM-centric development. · Proven track record with LangGraph, LangChain, or similar orchestration frameworks. · Expert in Python (asyncio, FastAPI preferred). · Hands-on experience building and deploying applications on AWS, particularly using Lambda, Fargate, S3, StepFunctions, and DynamoDB. · Familiarity with AWS Bedrock is a plus. · Strong understanding of agentic patterns, prompt chaining, tool calling, and More ❯
City of London, London, United Kingdom Hybrid / WFH Options
Rise Technical Recruitment Limited
become a trusted partner across a wide range of businesses. In this role you'll take ownership of the reliability and performance of large-scale date pipelines built on AWS, Apache Flink, Kafka, and Python. You'll play a key role in diagnosing incidents, optimising system behaviour, and ensuring reporting data is delivered on time and without failure. The … ideal candidate will have a strong experience working with streaming and batch data systems, a solid understanding of monitoring a observability, and hands-on experience working with AWS, Apache Flink, Kafka, and Python. This is a fantastic opportunity to step into a SRE role focused on data reliability in a modern cloud native environment, with full ownership of … incident management, architecture, and performance. The Role: *Maintaining and monitoring real-time and batch data pipelines using Flink, Kafka, Python, and AWS *Act as an escalation point for critical data incidents and lead root cause analysis *Optimising system performance, define SLIs/SLOs, and drive reliability *Woking closely with various other departments and teams to architect scalable, fault-tolerant More ❯
processes to improve efficiency, scalability, reliability and observability. Drive Engineering Excellence: Lead and manage all engineering activities across internal and external teams, ensuring high productivity and quality of execution. AWS Expertise: Strong expertise across AWS products, including S3, Glue, Spark, DBT, Terraform, and Redshift. Roadmap Prioritisation: Prioritize and manage engineering activities and personnel to deliver on a roadmap … Skills for the Data Operations Manager: Technology Degree with at least 5 years’ experience in data Proven experience in managing engineering teams in a fast-paced environment. Knowledge of AWS services and tools, including S3, StepFunctions, Spark, DBT, Terraform, and Redshift. Strong leadership and communication skills, with the ability to inspire and motivate a diverse team. More ❯