About the role
Responsibilities:
- Design, develop, and deploy production-ready AI agents and generative AI applications using Python, React, LangChain, LangGraph, and contemporary AI frameworks.
- Build and orchestrate complex agentic workflows, multi-agent systems, and LLM-powered solutions for enterprise use cases.
- Architect scalable end-to-end platforms encompassing APIs, middleware, agent orchestration layers, observability, and application integration.
- Develop and integrate REST and GraphQL APIs to connect AI systems with internal and external business applications.
- Implement best practices for model integration, prompt engineering, RAG pipelines, monitoring, performance optimization, and governance.
- Collaborate with cross-functional teams, including product, engineering, data, and business stakeholders, to deliver impactful AI solutions.
- Ensure reliability, scalability, security, and maintainability of AI-driven applications in cloud-native environments.
Requirements:
- Strong hands-on experience in Python and React development.
- Proven expertise in generative AI, large language models (LLMs), AI agents, and agentic architectures.
- Experience with LangChain, LangGraph, and related AI orchestration frameworks.
- Solid understanding of REST APIs, GraphQL, microservices, and middleware architectures.
- Experience building and deploying cloud-native applications in enterprise environments.
- Knowledge of observability, monitoring, debugging, and performance optimization for AI systems.
- Strong software engineering fundamentals, design patterns, and scalable architecture practices.
Preferred Qualifications:
- Experience with Databricks and AI/ML platform integration.
- Exposure to vector databases, RAG architectures, knowledge graphs, and AI governance frameworks.
- Familiarity with containerization technologies and modern cloud platforms such as AWS, Azure, or GCP.