• Design, develop, and deploy AI agentic applications by leveraging LLMs, prompt engineering, and Retrieval Augmented Generation (RAG) within agent workflow frameworks
• Collaborate with cross-functional teams to identify and prioritize project requirements
• Integrate AI models with Salesforce, Watsonx Assistant, Watsonx Orchestrate, Slack and other web applications using RESTful APIs and web frameworks such as Spring Boot or Flask/FastAPI.
• Develop and maintain relational and vector databases such as PostgreSQL and Milvus
• Stay up to date with the latest advancements in AI and machine learning, and apply this knowledge to improve our AI applications

Required Technical and Professional Expertise

• Proficiency in Prompt Engineering, LLMs, Retrieval Augmented Generation, and Python programming
• Experience with GitHub, software development, CICD, cloud and deployment database management systems such as MySQL or PostgreSQL ,vector database (Milvus, Weaviate) and graph database (Neo4j)
• Experience using LLMs in software applications, including prompting, calling, and processing outputs
• Experience with AI frameworks such as LangChain, Llamma Index, Crew.ai, Autogen, watsonx.ai and the models available in the platform
• Experience with LLM applications such as ChatGPT, Perplexity, RAG frameworks or engines (RAGflow, Haystack)

Preferred Technical and Professional Expertise

• Experience in designing and implementing large-scale AI solutions, including data ingestion, storage, processing, and deployment.
• Experience working on LLMs, Model Training & Evaluation, Performance Benchmarking.
• Experience in developing multi-agent applications using frameworks like Crew AI, AutoGen etc