Industry/Sector Not Applicable Specialism Oracle Management Level Senior Associate Job Description & Summary Job Title: Senior Associate – Generative AI Developer Experience: 5+ years of total IT experience, including 2–3 years in AI/ML or Generative AI development. Must have hands-on experience building, testing, and deploying LLM-based or agentic AI applications in production or pilot settings. Role Overview: The Senior Associate – Generative AI Developer will design, develop, and rigorously test end-to-end Generative AI and agentic AI applications. This role requires hands-on expertise with LLM APIs, RAG pipelines, prompt engineering, and multi-agent frameworks, combined with a disciplined approach to testing, performance monitoring, and optimization. Key Responsibilities: - LLM & GenAI Development: Design, develop, and maintain LLM-powered applications using APIs such as OpenAI, Azure OpenAI, Anthropic, or Cohere. Implement core GenAI workflows including summarization, classification, Q&A, and content generation. - Agentic AI Implementation: Build and orchestrate multi-agent systems using frameworks like CrewAI, LangGraph, OpenAI Agents SDK, or Azure AI Agent Framework. Implement inter-agent communication, task routing, and tool orchestration for complex workflows. - RAG & Embedding Pipelines: Implement retrieval-augmented generation pipelines involving embedding creation, chunking, and vector indexing using FAISS, Pinecone, Chroma, or Milvus. Ensure efficient retrieval for context-aware outputs. - Prompt Engineering & Techniques: Apply advanced prompting strategies such as Few-Shot Learning, Chain-of-Thought (CoT), ReAct, and CART to improve reliability and interpretability of model responses. - Testing & Validation: Establish automated and manual testing pipelines using TruLens, LangSmith, PromptLayer, or DeepEval to evaluate model quality, accuracy, safety, and factual grounding. Define and track metrics such as coherence, hallucination rate, and response diversity. - Performance Monitoring & Optimization: Implement cost-effective token management and model observability using logging and tracing frameworks. Continuously optimize prompts, retrieval logic, and memory mechanisms to improve efficiency. - Data Analysis & Preparation: Conduct EDA and pre-processing of textual datasets to ensure quality input for training, evaluation, and fine-tuning tasks. - Documentation & Collaboration: Create detailed design documents, maintain experiment logs, and collaborate with architects, data scientists, UI/UX engineers, and product managers to ensure solution alignment with business goals. - Continuous Learning: Stay up to date with new model releases (OpenAI GPT, Claude, Gemini, Mistral, LLaMA, etc.) and frameworks in the GenAI and agentic AI ecosystem. Key Skills & Competencies: - Strong proficiency in Python, LangChain, LlamaIndex, CrewAI, and LangGraph - Deep understanding of LLM architectures, tokenization, embedding models, and vector databases - Experience with prompt testing and evaluation frameworks (TruLens, LangSmith, PromptLayer, DeepEval) - Familiarity with bias mitigation, safety testing, and Responsible AI principles - Knowledge of MLOps/LLMOps practices for deploying and monitoring AI models - Strong analytical mindset, documentation discipline, and collaborative approach - Exposure to at least one major cloud AI platform (Azure, AWS, GCP, or OCI) Preferred Background: - Prior experience in building chatbots, intelligent assistants, summarizers, or document automation solutions using LLMs - Familiarity with open-weight model experimentation (LLaMA, Mistral, Falcon, etc.) - Exposure to multi-modal AI (text, image, code) and integration with enterprise data sources - Experience supporting GenAI projects through testing, benchmarking, and performance optimization Travel Requirements Not Specified Job Posting End Date