Agentic AI Engineer
Persistent
Persistent
Join our team as an Agentic AI Engineer and play a key role in developing end-to-end AI/ML solutions, Generative AI applications, and sophisticated agent-based automation workflows. This position offers a fantastic opportunity to work with cutting-edge technologies and contribute to innovative AI projects. We are committed to a values-driven, people-centric, and inclusive work environment, offering competitive benefits and a strong focus on talent development, including professional certifications and higher education support.
We champion diversity and inclusion, welcoming applications from all qualified individuals. Persistent provides a hybrid work model and flexible hours to accommodate various lifestyles, with an accessibility-friendly office environment equipped with ergonomic setups and assistive technologies.
Develop and deploy advanced Generative AI applications leveraging a variety of Large Language Models (LLMs) such as OpenAI, Azure OpenAI, Claude, Gemini, and Llama.
Design and implement sophisticated Agentic AI workflows using leading frameworks like CrewAI, AutoGen, LangGraph, or LangChain Agents.
Create robust Retrieval-Augmented Generation (RAG) pipelines, advanced vector search solutions, and embedding-based retrieval systems.
Build scalable AI services with Python, utilizing frameworks like FastAPI or Flask, and deploy them on cloud platforms including Azure, AWS, or GCP.
Collaborate closely with cross-functional teams to identify use cases and transform them into production-ready Generative AI solutions.
Implement effective strategies for hallucination reduction, prompt engineering, and rigorous model evaluation.
Integrate LLMs seamlessly with enterprise applications, APIs, and existing automation workflows.
Utilize vector databases such as FAISS, Pinecone, Chroma, or Weaviate for efficient semantic search capabilities.
Continuously monitor, evaluate, and optimize Generative AI models to enhance accuracy, performance, and cost-effectiveness.
Possess over 5 years of comprehensive experience in AI/ML, encompassing model development, data preprocessing, exploratory data analysis (EDA), training, and evaluation.
Demonstrate at least 2 years of hands-on experience specifically within Generative AI, including LLMs, embeddings, RAG, and building LLM-based applications.
Showcase a minimum of 6 months of practical experience with Agentic AI frameworks, such as CrewAI, AutoGen, LangGraph, or LangChain Agents.
Exhibit strong proficiency in Python and essential ML libraries, including Scikit-learn, Pandas, and NumPy.
Have experience with OpenAI APIs, Azure OpenAI, HuggingFace, and possess solid prompt engineering skills.
Familiarity with building scalable APIs using FastAPI, Flask, or Django is expected.
Possess hands-on knowledge of cloud services like Azure, AWS, or GCP for AI deployment.
Demonstrate a strong understanding of REST APIs, microservices architecture, and integration patterns.
Proficiency with Git, CI/CD pipelines, Docker, and best practices for model deployment is required.
Persistent Systems
IT Consulting