Job Description
- Design, develop, and deploy AI-powered applications and intelligent automation systems for enterprise use cases.
- Build and orchestrate multi-agent systems, autonomous agents, tool-using agents, and AI workflows.
- Develop production-grade LLM-powered applications, including conversational AI, chatbots, copilots, and AI automation.
- Design and implement enterprise-grade RAG architectures using appropriate retrieval, embedding, ranking, and context-management strategies.
- Integrate LLMs and AI capabilities using provider SDKs such as Claude Agent SDK and other leading LLM platforms.
- Build AI solutions using cloud-native AI services, with strong preference for AWS Bedrock experience.
- Develop MCP (Model Context Protocol) integrations to connect AI agents with enterprise tools, APIs, databases, and external systems.
- Design robust tool-calling and function-calling architectures for AI agents.
- Build reusable frameworks for agent orchestration, memory, context management, evaluation, and observability.
- Implement AI security and safety frameworks, including access control, data protection, prompt-injection mitigation, guardrails, and secure tool execution.
- Work with engineering teams to integrate AI capabilities into existing enterprise products and workflows.
- Evaluate LLM models, prompts, agents, and retrieval strategies based on accuracy, latency, reliability, and cost.
- Develop automated evaluation and monitoring mechanisms for LLM and agentic AI systems.
- Write clean, scalable, maintainable, and production-ready code.
- Participate in architecture discussions, technical design reviews, code reviews, and engineering best practices.
- Mentor engineers and contribute to building strong AI engineering practices within the organization.
Required Skills
['AI']
Additional Information
- Design, develop, and deploy AI-powered applications and intelligent automation systems for enterprise use cases.
- Build and orchestrate multi-agent systems, autonomous agents, tool-using agents, and AI workflows.
- Develop production-grade LLM-powered applications, including conversational AI, chatbots, copilots, and AI automation.
- Design and implement enterprise-grade RAG architectures using appropriate retrieval, embedding, ranking, and context-management strategies.
- Integrate LLMs and AI capabilities using provider SDKs such as Claude Agent SDK and other leading LLM platforms.
- Build AI solutions using cloud-native AI services, with strong preference for AWS Bedrock experience.
- Develop MCP (Model Context Protocol) integrations to connect AI agents with enterprise tools, APIs, databases, and external systems.
- Design robust tool-calling and function-calling architectures for AI agents.
- Build reusable frameworks for agent orchestration, memory, context management, evaluation, and observability.
- Implement AI security and safety frameworks, including access control, data protection, prompt-injection mitigation, guardrails, and secure tool execution.
- Work with engineering teams to integrate AI capabilities into existing enterprise products and workflows.
- Evaluate LLM models, prompts, agents, and retrieval strategies based on accuracy, latency, reliability, and cost.
- Develop automated evaluation and monitoring mechanisms for LLM and agentic AI systems.
- Write clean, scalable, maintainable, and production-ready code.
- Participate in architecture discussions, technical design reviews, code reviews, and engineering best practices.
- Mentor engineers and contribute to building strong AI engineering practices within the organization.