What are the responsibilities and job description for the Artificial Intelligence Engineer position at Polestar Analytics?
Polestar Analytics is hiring two AI Engineers to join our on-site delivery team in the tri-state area. You will be building and deploying production-grade AI agents and agentic systems on Microsoft Azure infrastructure, using Azure AI Foundry as the primary platform. This is a hands-on engineering role focused on designing, developing, and operationalizing AI agents that solve real business problems at enterprise scale.
Key Responsibilities
- Design, build, and deploy AI agents and multi-agent systems using Azure AI Foundry and the Azure AI Agent Service.
- Implement agentic architectures including tool use, function calling, retrieval-augmented generation, memory, planning, and orchestration patterns on Microsoft Azure infrastructure.
- Integrate agents with enterprise data sources, APIs, and downstream systems using Azure-native services such as Azure Functions, Logic Apps, API Management, AI Search, and Cosmos DB.
- Develop, evaluate, and iterate on prompts, model configurations, and agent workflows using Foundry's prompt flow, evaluation, and observability tooling.
- Apply responsible AI practices including content safety, grounding, evaluation metrics, and guardrails.
- Collaborate closely with the Solution Architect, data engineers, and client stakeholders to translate requirements into working agent-based solutions.
- Operationalize agents with proper CI/CD, monitoring, logging, versioning, and cost management.
- Continuously evaluate new capabilities in Azure AI Foundry and recommend their adoption where appropriate.
Required Qualifications
- 5 years of overall experience in software engineering, data science, machine learning, or AI engineering roles.
- 1 to 2 years of hands-on experience with AI agents, meaning building and deploying agentic systems rather than just calling LLM APIs.
- Strong working knowledge of Azure AI Foundry, including the model catalog, agent service, prompt flow, and evaluation tooling.
- Demonstrated experience deploying AI workloads on Microsoft Azure infrastructure including Azure OpenAI, Azure AI Search, Azure Functions, Azure Container Apps or AKS, and related services.
- Solid programming skills in Python, and ideally C# or TypeScript, for building agent backends and integrations.
- Experience with frameworks and patterns relevant to agentic systems such as function calling, tool orchestration, RAG, vector databases, prompt engineering, and evaluation.
- Strong grasp of LLM fundamentals including tokenization, context management, embeddings, and the trade-offs between fine-tuning and RAG.
- Familiarity with MLOps and LLMOps practices including CI/CD for AI, monitoring, evaluation pipelines, and prompt versioning.
- Excellent problem-solving skills and the ability to work directly with client stakeholders on-site.
- Must be based in or willing to work on-site in the NY/NJ tri-state area.
Preferred Qualifications
- Microsoft certifications such as Azure AI Engineer Associate (AI-102) or Azure Data Scientist Associate.
- Experience with Semantic Kernel, AutoGen, LangChain or LangGraph, or similar agent orchestration frameworks, especially in conjunction with Azure.
- Experience integrating agents with Microsoft 365, Copilot Studio, or Teams.
- Exposure to enterprise concerns including identity through Entra ID, networking, content safety, data governance, and compliance.
- Bachelor's or Master's degree in Computer Science, Data Science, Engineering, or a related field.