AI and Data Engineer

Job Title: AI and Data Engineer

Location: Jersey City, NJ (also open to NY/NJ, Tempe AZ, Tampa FL) — Hybrid, 3 days/week in office

Position Overview

We’re seeking an AI and Data Engineer with hands-on experience using GitHub Copilot and engineering AI agents that combine LLMs, prompt and context engineering, RAG, APIs, enterprise data sources, and governed tool execution to automate data, reporting, testing, and operational workflows. The ideal candidate has deep knowledge of current and emerging technologies and a passion for building elegant, responsible, secure, observable, and testable AI-driven solutions. You’ll work with technology and business leads to build and enhance critical enterprise data applications both on-prem and in the cloud (AWS), leveraging modern data platforms such as Snowflake and Starburst.

Roles and Responsibilities

• Use GitHub Copilot as a hands-on engineering environment to analyze code, design and implement production-quality changes, generate/maintain tests and documentation, debug failures, review changes, and verify outcomes with executable evidence
• Design, build, test, and operate AI agents that plan and execute multi-step workflows using LLM reasoning, structured prompts, context/memory, retrieval, APIs, data tools, and human approval gates
• Develop tool-enabled agents and MCP integrations that securely connect AI assistants to enterprise APIs and platforms (BI/reporting, data products, work-management systems, operational knowledge sources)
• Implement browser and UI automation agents for authenticated enterprise workflows, evidence capture, regression testing, and test generation/healing (Playwright, browser dev protocols)
• Define agent evaluation, observability, and safety controls — grounded-response checks, deterministic tool contracts, structured outputs, least-privilege credential handling, approval checkpoints, test datasets, execution traces, failure recovery
• Develop and implement data mesh and data fabric architectures for decentralized data management and access
• Design, build, and deploy cloud-native AI, data, and analytics solutions on AWS (serverless, containerized, event-driven)
• Develop automated deployment pipelines and cloud integrations for secure, scalable delivery of AI agents, data products, and reporting solutions
• Build data and BI development agents that generate/validate SQL, DAX, semantic models, reports, data-product specs, quality tests, and deployment artifacts while preserving governance and auditability
• Develop user/business personas aligned with data requirements
• Translate functional specifications into technical designs with business users
• Work cross-functionally on prototypes, design artifacts, components, SIT/UAT testing, triage, and bug fixing
• Provide problem-solving expertise and complex data analysis for BI integration designs
• Ensure high quality and optimum performance of data systems

Job Requirements

Bachelor’s degree (or foreign equivalent) in IT, Information Systems, Computer Science, Software Engineering, or related field. Financial services/banking industry experience preferred.

• 2+ years hands-on experience with GitHub Copilot or similar AI-assisted engineering tools across the SDLC (requirements, coding, refactoring, testing, debugging, documentation, code review, verification)
• 2+ years hands-on experience designing and building Agentic AI solutions — prompt/context engineering, LLMs, RAG, structured tool/function calling, APIs, memory/state management, human-in-the-loop controls, AI governance
• 3+ years developing and deploying cloud-native applications on AWS (serverless, container, event-driven, security, CI/CD)
• Hands-on programming in Python, Java, TypeScript, and SQL — able to design agent tools, API clients, MCP servers, CLI workflows, typed data contracts, and automated tests
• Experience integrating agents with enterprise authentication, APIs, databases, knowledge repositories, BI platforms, and browser automation while protecting credentials, sensitive data, and audit trails
• Demonstrated ability to evaluate agent quality through unit/integration/behavioral/end-to-end tests, diagnose hallucinations and tool failures, instrument execution, and improve prompts/retrieval/context using evidence

Preferred Background

• 5+ years with data virtualization, data mesh, data fabric, and federated querying platforms (Denodo, Starburst, or OSS)
• 5+ years as a Report Visualiz…