Required Skills: CI/CD, Python, AI frameworks, REST APIs

Job Description

• Design, develop, and deploy production-grade AI/ML applications powered by Large Language Models (LLMs).
• Build end-to-end intelligent systems using Python and modern AI frameworks.
• Architect and implement Retrieval-Augmented Generation (RAG) solutions using enterprise data sources.
• Develop and optimize embedding pipelines and vector database integrations for semantic search and knowledge retrieval.
• Create multi-step, tool-enabled agentic workflows capable of planning, reasoning, execution, and memory management.
• Utilize frameworks such as LangChain and related agent orchestration tools to build scalable AI solutions.
• Integrate AI applications with REST APIs, backend services, databases, and third-party platforms.
• Design scalable, secure, and maintainable system architectures for AI-powered products.
• Deploy and manage AI workloads across cloud environments and distributed systems.
• Establish evaluation frameworks to measure model accuracy, reliability, latency, and cost efficiency.
• Implement monitoring, logging, and observability solutions for AI applications in production.
• Optimize prompts, workflows, and model interactions to improve performance and user experience.
• Collaborate with product, engineering, and business stakeholders to translate requirements into AI-driven solutions.
• Troubleshoot and resolve issues related to model performance, data quality, and system integration.
• Follow software engineering best practices, including testing, version control, CI/CD, and code reviews.
• Stay current with advancements in LLMs, agentic AI, vector databases, and emerging AI technologies.
• Contribute to architecture decisions, technical documentation, and knowledge sharing across teams.
• Ensure AI solutions meet enterprise standards for scalability, security, governance, and compliance