AWS Data Engineer

Role - AWS Data Engineer Location - London, UK (Hybrid) Type - Contract (Inside IR35) Job Description: Job Summary We are looking for a Senior AWS Data Developer with 7–10 years of experience building cloud-native data and AI applications on AWS. Strong expertise in Python, serverless data engineering, RAG, Agentic AI, LangChain, LangGraph, FastAPI, LLMOps, prompt/context engineering, and scalable data platforms., LangGraph State Management, Model Context Protocol (MCP), Vector Databases (FAISS, ChromaDB, Pinecone, Milvus), AI Evaluation & Guardrails, AI Observability Key Responsibilities • Design and build scalable, serverless data pipelines and AI-powered applications on AWS • Architect and implement RAG (Retrieval-Augmented Generation) and Agentic AI solutions using LangChain, LangGraph, and FastAPI • Build multi-agent orchestration systems and tool-calling patterns • Integrate vector databases (FAISS, ChromaDB, Pinecone) for semantic search and knowledge retrieval • Implement prompt engineering and context engineering strategies for LLM-driven workflows • Establish LLMOps practices — model versioning, evaluation pipelines, AI guardrails, and observability (LangSmith, CloudWatch) • Develop Python-based ETL/ELT frameworks for large-scale batch and streaming data processing • Build reusable APIs (FastAPI), shared libraries, and common data frameworks consumed across teams • Implement Model Context Protocol (MCP) for structured LLM interactions and tool integration • Set up AI evaluation and monitoring — response quality metrics, hallucination detection, latency tracking • Optimize application performance, cost, and reliability across data and AI workloads • Troubleshoot production issues across data pipelines and AI services; participate in code reviews • Collaborate with architects, ML engineers, DevOps, and business stakeholders to deliver end-to-end solutions Required Skills Programming: Python, PySpark, SQL, FastAPI, OOP, Async Programming, AWS: Lambda, S3, SQS, SNS, Step Functions, EventBridge, Glue, Athena, DynamoDB, API Gateway, IAM, CloudWatch, Secrets Manager, Bedrock, Sagemaker AI Engineering: LangChain, LangGraph, LangSmith (monitoring), RAG, Agentic RAG, AI Agents, Multi-Agent Systems, Prompt Engineering, Context Engineering, LLMOps, Agentic Orchestration. Data Engineering: Apache Spark, Apache Iceberg, ETL/ELT, Parquet, Schema Evolution. DevOps: Docker, Git, LangGraph State Management, Model Context Protocol (MCP), Vector Databases (FAISS, ChromaDB, Pinecone, Milvus), AI Evaluation & Guardrails, AI Observability Required Experience • 7+ years of software/data application development experience • 5+ years of hands-on AWS development (Lambda, Step Functions, S3, Glue, Athena, Bedrock, SageMaker) • Strong expertise in Python, SQL, and FastAPI development • Experience building serverless, event-driven data and AI applications on AWS • Hands-on experience with RAG pipelines, Agentic AI, and multi-agent orchestration (LangChain, LangGraph) • Experience with vector databases (FAISS, ChromaDB, Pinecone, Milvus) and semantic retrieval patterns • Proficiency in prompt engineering, context engineering, and LLM integration • Experience with LLMOps — model evaluation, AI guardrails, observability (LangSmith), and deployment automation • Experience developing Spark/PySpark-based data processing solutions • Experience working with Apache Iceberg or similar lakehouse table formats • Familiarity with AI evaluation frameworks, hallucination detection, and response quality monitoring • Experience implementing CI/CD pipelines • Experience working in Agile development environments Preferred Qualifications • AWS Certified Developer – Associate • AWS Certified Data Engineer – Associate • AWS Certified Solutions Architect – Associate