Senior AI Engineer (Agentic AI / AWS)

About Gramian

Gramian Consultancy is a boutique consultancy specializing in IT professional services and engineering talent solutions. With a strong background in software engineering and leadership, we help companies build high-performing teams by matching them with professionals who truly fit their needs.

About the Role

Our client is a Big4 Consultancy group that works with leading financial institutions on AI-driven transformation, automation, advanced analytics, and financial crime prevention. Their work spans intelligent fraud detection, AML/KYC modernization, autonomous workflows, enterprise AI platforms, and the secure industrialization of AI in highly regulated environments.

We are looking for Senior AI Engineers to design, build, and deploy production-grade autonomous agents, multi-agent systems, and LLM-powered enterprise applications. The role will work across multiple delivery squads and focus on reusable architecture, agent orchestration, tool integration, cloud deployment, and evaluation of long-running AI workflows.

CONTRACT: Contractor assignment, expected October 2026 – July 2027, with extension available (and retainer rate)

COMMITMENT: Full-time

LOCATIONS: REMOTE 100%, Europe-based and EU authorization

PROCESS: Initial qualification followed by technical and client interviews

NOTES: Fluent English is required. Must have authorization for EU work.

Responsibilities

- Architect and build production-grade autonomous AI agents and multi-agent orchestration frameworks. - Develop reusable agent patterns and technical standards across multiple engineering squads. - Integrate LLMs with APIs, databases, proprietary tools, and enterprise systems. - Implement reliable tool-calling and structured-output workflows. - Design and optimize prompt strategies, context management, memory, and agent state. - Build stable, long-running agent workflows with appropriate error handling and recovery mechanisms. - Implement monitoring, logging, tracing, and evaluation frameworks for agent behavior and model outputs. - Support the deployment of AI systems on public cloud infrastructure, primarily AWS. - Apply MLOps/AIOps practices across versioning, testing, monitoring, and evaluation. - Collaborate with engineering, data, cloud, and business teams to deliver secure and scalable AI solutions.

Requirements

- 5–10 years of professional software, data, or AI engineering experience. - Strong hands-on development experience with Python. - Proven experience designing and integrating LLM-powered or agentic AI applications. - Experience with agent orchestration frameworks such as LangChain, AutoGen, CrewAI, or comparable technologies. - Strong experience with enterprise AI integration patterns including MCP, A2A, structured outputs, tool calling, or skills-based architectures. - Professional experience designing and deploying AI solutions on public cloud platforms, preferably AWS. - Experience with MLOps/AIOps practices, including versioning, testing, monitoring, and evaluations. - Fluent professional English.