AI Engineer

Proactive Technology Management is seeking a highly innovative Generative AI Product Engineer to join our dynamic and growing team. In this role, you will be responsible for developing, deploying, and optimizing next-generation AI agents and copilots that integrate with enterprise systems to automate and streamline complex business processes. You will leverage cutting-edge technologies such as LangChain , DSPy , OpenAI APIs , and Ollama , and build agent-based systems that transform how businesses manage their workflows, customer interactions, and data insights. The ideal candidate will be proficient in building intelligent, agentic AI systems that utilize a range of AI models for everything from simple task automation to complex decision-making pipelines. You'll play a critical role in shaping our AI strategy by designing RAG-enabled (Retriever-Augmented Generation) agent pipelines, orchestrating LLM-driven workflows , and ensuring seamless integration of AI solutions with existing business infrastructures. This position demands a blend of creativity, technical expertise, and problem-solving skills to convert both business and technical requirements into tangible, automated solutions that deliver measurable business value. Key Responsibilities Design and Implement Agent-Based Systems: Create intelligent AI agents using DSPy , LangChain , Ollama , and/or OpenAI APIs to orchestrate workflows, perform automated tasks, and optimize business processes. Develop RAG-Enabled Pipelines: Build and refine complex pipelines using Retriever-Augmented Generation (RAG) for knowledge retrieval, enabling agents to provide accurate, contextually relevant information in real-time. Automate Business Workflows: Use agentic AI frameworks to automate repetitive business processes, reducing manual workloads while improving decision-making and task completion times. Orchestrate AI-Driven Task Execution: Develop and maintain compound agent pipelines that integrate retrieval-based agents, generative models, and traditional AI functions to tackle multi-step workflows. Integrate AI with APIs and Data Sources: Seamlessly integrate AI agents with external data sources, web services, and RESTful APIs , ensuring that agents can access, retrieve, and process structured data in real-time. Optimize and Monitor Performance: Use observability tools to monitor agent performance, ensuring high availability, scalability, and fault tolerance of AI-driven systems. Ensure proper logging, monitoring, and alerting mechanisms using Azure-based services such as Azure Monitor and Log Analytics . Deploy and Scale Using Docker and Cloud: Leverage Docker , Azure Container Apps , and Azure Functions to deploy scalable agentic AI solutions. Ensure that deployments are efficient, secure, and capable of scaling based on workload. Stay Current on Emerging AI and Automation Trends: Keep up with advancements in multimodal AI , vector databases (such as LanceDB ), and evolving AI orchestration techniques to continuously improve the solutions you develop. Collaborate with Stakeholders: Work closely with business leaders and non-technical stakeholders to gather requirements and translate them into efficient, AI-driven workflows that deliver clear business benefits. Essential Skills and Experience Proven experience in building agentic AI systems using LangChain , DSPy , and/or OpenAI APIs , and/or Ollama . Strong expertise in Python (including interfacing with databases and datastores, functional and object-oriented design patterns, and ORM and ML frameworks) and proficiency with both locally run and cloud-based generative AI models and APIs , including those from OpenAI (e.g. GPT-4o), Meta (e.g. Llama 3), and Microsoft Research (e.g. Phi). Deep knowledge of RAG pipelines and retrieval-augmented generation techniques for knowledge-based systems. Strong understanding of vector databases like LanceDB and experience integrating them into AI workflows to improve agent intelligence and retrieval capabilities. Demonstrated ability to deploy, monitor, and optimize AI solutions using Docker and cloud platforms like Azure . Fluency in designing scalable, multi-agent systems that can execute tasks autonomously and/or in coordination with other agents. Familiarity with Azure Cognitive Services , Azure Functions , and serverless architectures to orchestrate and scale AI workflows. Ability to communicate complex technical concepts clearly to non-technical stakeholders in English. Preferred Skills Familiarity with Streamlit for creating low-code generative AI frontends in Python and rapidly prototyping solutions. Experience with multimodal AI systems that integrate text, image, and structured data into decision-making processes. Expertise in deploying AI solutions using Azure Container Apps and other scalable cloud architectures. Familiarity with tools like LangServe and Ollama for deploying generative AI-based solutions at scale and PyCaret for performing classical ML tasks. Experience with CI/CD pipelines (such as Bitbucket Pipelines ) and project management platforms like Monday.com for efficient development and release management. Familiarity with AI observability and telemetry tools for maintaining high availability and reliability in agent-based systems, ensuring comprehensive logging and analytics for actionable insights. #J-18808-Ljbffr