Backend AI Engineer
Persistent
Persistent
Join our dynamic team as a Backend AI Engineer, focusing on crafting advanced AI and Agentic AI applications. You will leverage your expertise in TypeScript, Python, and Node.js to build robust, scalable backend services. This role involves integrating cutting-edge technologies like Large Language Models (LLMs), AI Agent frameworks, enterprise systems, and cloud-native infrastructure to deliver innovative solutions. We are a leading digital engineering and modernization partner, recognized for our AI-led approach and commitment to client success. Our culture fosters talent development and embraces diversity, offering a flexible and inclusive work environment.
We are dedicated to continuous growth, both for our clients and our employees. With a strong track record of sequential growth and a global presence across 18 countries, we empower our 27,500+ team members to drive transformation. Recognized as a Leader in multiple PEAK Matrix Assessments and the Fastest Growing IT Services Brand Globally, Persistent offers a platform to work with industry leaders and shape the future of technology.
Design and implement scalable backend AI services, APIs, and integration components using TypeScript, Python, and Node.js. Build backend services that power AI Agents, Copilots, Assistants, and automated workflows. Develop REST APIs, asynchronous services, event-driven workflows, and real-time streaming capabilities. Architect robust service designs capable of handling enterprise-scale AI workloads. Create Agentic AI workflows utilizing frameworks like LangChain, LangGraph, and AutoGen. Implement intelligent agent functionalities including tool and function calling, task planning, memory management, and error recovery. Design graph-based workflow automation and multi-agent systems. Integrate various LLMs, including OpenAI, Qwen, and other enterprise-approved models. Engineer secure, scalable AI applications and optimize LLM response quality and system performance. Develop enterprise-grade RAG pipelines, document parsing, embedding, and retrieval mechanisms. Design and maintain semantic data structures, knowledge graphs, and metadata models. Deploy cloud-native AI applications on AWS, utilizing containerization with Docker and Kubernetes. Implement CI/CD pipelines, automated deployments, and robust monitoring and logging solutions. Collaborate with cross-functional teams, including AI Product Owners, Data Scientists, and business stakeholders, to drive solution design and best practices.
Proven experience developing backend AI services and APIs using TypeScript, Python, and Node.js. Expertise in building scalable backend services that integrate AI agents, LLMs, and enterprise systems. Strong understanding of REST APIs, asynchronous programming, event-driven architectures, and microservices. Hands-on experience with AI agent frameworks such as LangChain, LangChain.js, LangGraph, CrewAI, or AutoGen. Deep knowledge of Large Language Models (LLMs), prompt engineering, tool calling, and AI evaluation techniques. Experience integrating OpenAI-compatible models and other enterprise AI platforms. Familiarity with cloud-native development, particularly AWS services, Docker, and Kubernetes. Ability to design and implement RAG pipelines, including document processing, embedding, and retrieval strategies. Experience building and maintaining knowledge graphs, metadata models, and semantic data structures. Proficiency in developing and implementing monitoring, logging, and observability solutions using tools like OpenTelemetry. Excellent collaboration and communication skills, with the ability to work effectively in cross-functional teams. Experience working with laboratory, scientific, or automation environments is a plus. Knowledge of Knowledge Graph technologies and distributed systems is beneficial.
Persistent Systems
IT Consulting