Generative AI Engineer – Agent Development Specialist

Job Title: Generative AI Engineer – Agent Development Specialist (Only on our W2) Location: Remote (USA) Job Type: Long-term contract on our W2 Overview • We are looking for an experienced Generative AI Engineer skilled in agent-based system development. • This position focuses on designing, implementing, and optimizing intelligent multi-agent workflows using advanced AI models and architectures. • The ideal candidate is proficient in Python, AI agents, vector databases, and multi-agent frameworks, and is eager to advance autonomous AI agents in production settings. Key Responsibilities • Design, build, and maintain autonomous or semi-autonomous AI agents using frameworks such as Lang Graph, Autogen, CrewAI, or Bedrock (Lang graph preferred) • Engineer sophisticated prompting strategies to drive consistent, effective agent performance across dynamic use cases. • Architect end-to-end solutions that integrate vector databases (e.g., Azure AI Search, FAISS, Pinecone) with real-time or batch ETL pipelines to power agent memory and retrieval-augmented generation (RAG). • Leverage Cosmos DB and other NoSQL data stores to manage large-scale, unstructured, and semi-structured data efficiently. • Collaborate cross-functionally to integrate agent systems into broader products, APIs, and workflows. • Continuously monitor the evolving GenAI landscape, evaluating new models, tools, protocols, and design patterns. • Participate in code reviews, maintain code quality standards, and follow Git/GitHub workflows, including branching, pull requests, and CI/CD practices. • Conduct performance tuning and safety evaluations of AI agents across a variety of operational environments. Required Qualifications • Strong programming skills in Python, including OOP principles and production-level code design. • Demonstrated experience with prompt engineering techniques for large language models (LLMs) like GPT models, Claude, Gemini, or open-source equivalents. • Deep understanding of AI agent concepts, including memory management, planning, tool use, autonomous task execution, and evaluation metrics. • Working knowledge of multi-agent orchestration frameworks, preferably Lang Graph, but experience with Autogen, CrewAI, or similar is also valuable. • Experience with vector databases (e.g., Azure AI Search, Pinecone, FAISS, Chroma) for embedding storage and semantic search. • Understanding of ETL processes and data transformation pipelines in both batch and streaming architectures. • Familiarity with NoSQL databases, specifically Cosmos DB, and designing scalable schemas for AI-driven systems. • Proficiency with Git/GitHub, including use of Gitflow or similar collaborative workflows. • Demonstrated ability to stay current on the latest GenAI models, protocols (e.g., OpenAI Assistants, Function Calling, Lang Chain Agents), and research trends. Preferred Qualifications • Experience deploying agents in cloud environments (Azure, AWS, or GCP). • Familiarity with model fine-tuning, embedding generation, and OpenAI plugin/tool calling. • Exposure to observability and evaluation techniques for AI systems (e.g., human-in-the-loop, automated feedback loops). • Plus - Contributions to open-source AI projects or publications in the field. • Python • Prompt engineering • Understanding of AI agents • Understanding of vector databases • Understanding of current events in the GenAI field (most up-to-date models, ideally also awareness of how to use non-OpenAI models like Gemini and Claude) • Understanding of Lang Graph (Ideally Autogen) • Understanding of Cosmos DB and NoSQL • Bonus: AngularJS and Typescript (just for some specific use cases we're looking into right now, but really not required)