Lead AI Engineer (IRC301083)

We are looking for a Senior/Lead AI Engineer specializing in Agentic AI and LLM-based systems to help design and implement production-grade AI capabilities.

The role combines strong backend engineering expertise with hands-on Generative AI experience. You will be responsible for building reliable AI services, integrating LLM-based solutions into enterprise applications, and establishing engineering practices required to operate AI features at scale.

You will work closely with AI engineers, backend developers, architects, and product teams to deliver secure, scalable, and maintainable AI solutions.

Requirements

• 5+ years of software engineering experience with strong backend/distributed systems background.
• 2+ years of experience building and operating production Generative AI / LLM-based systems.
• Strong Python engineering skills and experience developing production services.
• Hands-on experience with LLM application development and AI agent frameworks.
• Experience with frameworks such as LangGraph, Strands Agents, Semantic Kernel, or similar technologies.
• Experience designing AI workflows, tool integrations, and agent orchestration patterns.
• Strong understanding of LLM capabilities, limitations, model selection, and optimization strategies.
• Experience designing evaluation approaches for AI systems, including quality measurement and regression testing.
• Experience building secure AI solutions considering data privacy, access control, and responsible AI practices.
• Strong AWS experience, including services such as Amazon Bedrock.
• Experience with Infrastructure as Code (Terraform / CloudFormation).
• Experience designing event-driven architectures and scalable cloud services.

Job responsibilities

• Design and develop production-grade LLM-powered applications and agentic AI workflows.
• Build AI services using Python and modern AI frameworks.
• Develop reliable backend services supporting AI-driven functionality.
• Design and implement integrations between AI services and enterprise applications.
• Work with LLM platforms and evaluate model capabilities, performance, and cost trade-offs.
• Develop AI agent workflows including tool integrations, memory/session management, and orchestration.
• Establish best practices for prompt management, AI evaluation, testing, and continuous improvement.
• Design scalable solutions for AI output validation, monitoring, and production support.
• Collaborate with application teams to define API contracts and integration patterns.
• Support deployment and operation of AI workloads in cloud environments.