AI Engineer – Full-Stack

This is a fully remote position, open to applicants in United States.

📋 Description

• Collaborate directly with business stakeholders to analyze workflows, identify pain points, and assess current-process costs.

• Utilize AI research tools to establish benchmarks for industry standards, regulations, and best practices.

• Define challenges, outline project scope, establish success metrics, and set delivery timelines; assertively address any scope that does not align with the timeline.

• Create and present functional proofs of concept within the initial days of the project.

• Engage in live iterations with users to determine whether to pivot, phase, or cease development.

• Design and implement full-stack web applications, AI agents, workflow automations, integrations, and data pipelines.

• Draft specifications and prompts, decompose tasks into AI-executable segments, manage parallel agents, and review as well as refine outputs.

• Leverage AI to generate tests, analyze code, identify bugs, and create documentation.

• Construct reusable prompts, skills, templates, and components.

• Prepare documentation related to information security, data privacy, and legal compliance.

• Oversee change requests through the established change control process.

• Deploy applications to enterprise cloud environments with features such as SSO, role-based access, logging, monitoring, and cost management.

• Provide user training, develop user and support guides, and secure business sign-off.

• Manage multiple projects simultaneously, adhering to staggered timelines and fixed completion targets.

• Monitor work on a daily basis and promptly identify and escalate risks and blockers.

⛳️ Requirements

• Proficient daily use of AI coding tools (Claude Code, Cursor, Copilot, or similar), including agentic, multi-file, and multi-step development.

• Expertise in prompt and context engineering: system prompts, structured outputs, few-shot design, and managing the context window.

• Familiarity with LLM application patterns: RAG, tool use/function calling, agents and multi-agent orchestration, MCP servers, and connectors.

• Knowledge of evaluation and guardrails: test sets, output validation, hallucination checks, prompt injection and data-leakage defenses, and human-in-the-loop design.

• Working understanding of model selection, latency, token cost, and rate-limit trade-offs across major LLM APIs.

• Experience with document and data AI.

• Proficient in React/TypeScript or similar, responsive UI, and component libraries.

• Skilled in Python with FastAPI/Flask and/or Node.js, REST/GraphQL APIs, and async and background jobs.

• Knowledgeable in SQL and NoSQL databases, data modeling, ETL, and basic analytics and reporting.

• Experience with enterprise APIs, webhooks, OAuth, and platforms like Microsoft 365/SharePoint, Salesforce, SAP, and ServiceNow.

• Proficient in workflow automation using Power Automate, Logic Apps, n8n, or similar tools.

• Experience in cloud deployment on Azure, AWS, or GCP; familiarity with App Services, Docker, and serverless functions.

• Knowledge of Git, CI/CD pipelines, environment management, and secrets management.

• Familiarity with SSO, Entra ID/Azure AD, OAuth2/OIDC, and role-based access.

• Understanding of secure coding practices, OWASP guidelines, and handling sensitive and personal data.

• Experience with logging, monitoring, and alerting for production support.

• Proven track record of meeting fixed deadlines while managing multiple projects concurrently.

• Strong skills in scoping and prioritization.

• Excellent communication skills with non-technical stakeholders.

• Experience guiding solutions through enterprise security, privacy, legal, and change management processes.

• Independent, ownership-driven work style.

• Minimum of 3 years of experience in building and deploying full-stack applications to production.

• A portfolio or examples of AI-driven solutions delivered end-to-end, including timelines and outcomes.

• At least one LLM-powered application or agent currently in production use.

• U.S. citizenship is required; Gruve is unable to provide sponsorship.

• Preferred: prior experience in FDE, solutions engineering, technical consulting, or internal-tools development.

• Preferred: familiarity with regulated industries and knowledge of GDPR, ISO 27001, SOC 2, or GxP.

• Preferred: experience in developing internal AI platforms, shared skill libraries, or reusable agent frameworks.

• Preferred: knowledge of Python data tools and basic machine learning concepts.

🏝️ Benefits

• A dynamic work environment with robust customer and partner networks.

• A culture that promotes innovation, collaboration, and ongoing learning.

• A diverse and inclusive workplace.

• Commitment to equal opportunity employment.