GenAI Engineer (Agent Development)

Generative AI Engineer – Agent Development Specialist Our Big 4 client is seeking an experienced Generative AI Engineer Consultant with expertise in agent-based system development to support a major client. In this role, you will design, implement, and optimize intelligent multi-agent workflows that power next-generation applications. The ideal candidate is highly skilled in Python, AI agents, vector databases, and multi-agent orchestration frameworks, and is motivated to bring autonomous AI agents into production environments. Key Responsibilities • Design, build, and maintain autonomous and semi-autonomous AI agents using frameworks such as LangGraph (preferred), Autogen, CrewAI, or Bedrock. • Develop sophisticated prompting strategies to ensure consistent, reliable, and effective agent performance across dynamic use cases. • Architect end-to-end agent solutions integrating vector databases (e.g., Azure AI Search, FAISS, Pinecone, Chroma) with real-time and batch ETL pipelines for retrieval-augmented generation (RAG). • Leverage CosmosDB and other NoSQL data stores to manage unstructured and semi-structured datasets at scale. • Collaborate with product, engineering, and data teams to integrate AI agents into APIs, applications, and enterprise workflows. • Stay up to date with the latest GenAI models, frameworks, and design patterns, and evaluate their applicability to production use cases. • Conduct performance tuning, observability, and safety evaluations of AI agents across varied environments. • Participate in code reviews and maintain engineering best practices using Git/GitHub workflows (branching, PRs, CI/CD). Required Qualifications • Strong programming skills in Python with a solid grasp of OOP principles and production-level code. • Hands-on experience with prompt engineering techniques for LLMs (GPT, Claude, Gemini, or open-source equivalents). • Deep understanding of AI agent concepts: memory management, planning, tool use, autonomous task execution, and evaluation metrics. • Experience with multi-agent orchestration frameworks, ideally LangGraph, but Autogen, CrewAI, or similar are also valuable. • Proficiency with vector databases (Azure AI Search, Pinecone, FAISS, Chroma) for embeddings and semantic search. • Understanding of ETL processes and data pipelines (batch and streaming). • Familiarity with NoSQL databases (CosmosDB preferred) and scalable schema design. • Experience with Git/GitHub workflows, including Gitflow or similar collaborative practices. • Strong awareness of current GenAI trends, models, and protocols (e.g., OpenAI Assistants, function calling, LangChain Agents). Preferred Qualifications • Experience deploying AI agents in cloud environments (Azure, AWS, or GCP). • Familiarity with fine-tuning models, embeddings generation, and plugin/tool calling in LLM ecosystems. • Exposure to AI evaluation methods, such as human-in-the-loop and automated feedback loops. • Contributions to open-source AI projects or publications in the field. • Bonus: Exposure to AngularJS and TypeScript for specific use cases. Core Skills • Python • Prompt Engineering • Multi-Agent Orchestration (LangGraph, Autogen, CrewAI, etc.) • Vector Databases (Azure AI Search, Pinecone, FAISS, Chroma) • NoSQL / CosmosDB • ETL & Data Pipelines • Agile / Scrum (CSP, CSPO) • RESTful APIs • Conversational Agents & Application Architecture #Dice