AI Engineer
Our client helps leading Tier 1 banks and insurance companies transform their operations through Artificial Intelligence, automation, and advanced analytics, with a particular focus on Anti-Financial Crime (AFC).Their core areas of expertise include AI-driven fraud prevention, Anti-Money Laundering (AML), and Know Your Customer (KYC). They design and implement intelligent solutions that enhance detection capabilities, automate investigations and customer due diligence, improve operational efficiency, and help financial institutions respond to evolving regulatory requirements.
As part of the project, you will work at the intersection of AI engineering, cloud technologies, data science, business transformation, and financial services, helping some of the world’s largest financial institutions solve complex challenges in highly regulated and mission-critical environments.
The Role: Senior AI Engineer with strong hands-on expertise in Agentic AI, LLM integrations, Python, and cloud-based AI platforms. You will be responsible for designing, building, and deploying production-grade autonomous AI agents and multi-agent orchestration frameworks across four parallel engineering squads.
You will help establish reusable patterns and standards for AI agent development while working closely with multiple engineering teams to ensure solutions are scalable, observable, secure, and production-ready.
Key Responsibilities
- Develop autonomous AI agents and multi-agent systems for complex enterprise workflows.
- Design and implement agent orchestration frameworks using technologies such as LangChain, AutoGen, CrewAI, or similar.
- Integrate Large Language Models (LLMs) with external APIs, enterprise databases, proprietary toolkits, and business systems.
- Design functional tool-calling capabilities that enable agents to interact with external systems and execute business workflows.
- Work with modern agent interoperability approaches, including MCP, A2A, structured outputs, and agent skills.
- Optimize prompt engineering, context management, state management, and long-running agent workflows.
- Implement MLOps/AIOps practices, including versioning, automated testing, monitoring, and evaluations.
- Build monitoring, logging, tracing, and evaluation frameworks to understand agent decision paths and model outputs.
- Design and deploy AI solutions on public cloud infrastructure, with a particular focus on AWS.
- Collaborate with AI Engineers, Data Scientists, Platform Engineers, and business stakeholders to move AI solutions from experimentation into production
Requirements
- Strong commercial experience with Python.
- Strong hands-on experience designing and integrating AI/LLM solutions into enterprise applications.
- Practical experience developing Agentic AI solutions, autonomous agents, or multi-agent systems.
- Experience with agent orchestration frameworks such as LangChain, AutoGen, CrewAI, or equivalent.
- Strong understanding of MCP (Model Context Protocol), A2A, structured outputs, tool calling, and agent skills.
- Experience integrating LLMs with APIs, databases, enterprise applications, and external tools.
- Strong understanding of prompt engineering, context management, and agent state management.
- Experience with MLOps/AIOps practices, including versioning, testing, monitoring, tracing, and AI evaluations.
- Hands-on experience deploying AI solutions to public cloud platforms.
- Strong understanding of production engineering principles, including scalability, observability, reliability, and security.
What We Offer
At TEAM International, you’ll have the opportunity to work on impactful projects alongside top professionals, collaborate with international clients, and leverage the latest technologies.
- Work with global IT talent in a flexible engagement model
- Be part of challenging, high-impact projects with modern tech stacks
- Full compliance with security and regulatory standards
- A supportive, collaborative, and people-first environment