AI Engineer – Full-Stack (Forward Deployed)

About Gruve Gruve is an innovative software services startup dedicated to transforming enterprises to AI powerhouses. We specialize in cybersecurity, customer experience, cloud infrastructure, and advanced technologies such as Large Language Models (LLMs). Our mission is to assist our customers in their business strategies utilizing their data to make more intelligent decisions. As a well-funded early-stage startup, Gruve offers a dynamic environment with strong customer and partner networks. About the Role We are hiring a hands-on, AI-native full-stack engineer who works directly with business teams and owns each solution end to end, from the first conversation to production. This is not a product-team role on a shared roadmap. You will take a business problem, design and build the solution yourself, and ship it to production against fixed, short deadlines. AI is how you work: you will use Claude, Claude Code, agents and MCP to plan, build, test, document and deploy at a pace traditional development can't match, without lowering the quality bar. The role follows the Forward Deployed Engineer (FDE) model: embedded with the business, close to the users, and accountable for the outcome and the date. Key Responsibilities

1. Discovery Work directly with business stakeholders to map their workflows, pain points and the cost of the current process. Use AI research tools to quickly benchmark industry standards, regulations and best practices for the process. Turn unclear requests into a defined problem, scope, success measure and delivery date. Push back early when scope doesn't fit the timeline.
2. Rapid POC Build and demo a working POC within the first couple of days, using AI to generate scaffolding, UI, data models and integrations in hours. Iterate live with users, and decide quickly whether to pivot, phase or stop.
3. AI-accelerated build Develop full-stack solutions: web apps, AI agents, multi-step workflow automations, integrations and data pipelines. Run AI-driven development workflows. Write precise specs and prompts, break work into tasks the AI can execute, run parallel agents, and steer, review and correct their output. Use AI to generate unit, integration and end-to-end tests, review code, find bugs and produce documentation, so quality keeps pace with speed. Build reusable prompts, skills, templates and components that make each new project faster than the last.
4. Production release on deadline Prepare information security, data privacy and legal documentation (AI-assisted drafting is expected) and see the reviews through. Raise and manage change requests through the change control process. Plan around review lead times so release dates hold. Deploy to enterprise cloud environments with SSO, role-based access, logging, monitoring and cost controls in place.
5. Handover and support Train users, produce concise user and support guides, and get business sign-off. Run several projects at once on staggered timelines with fixed completion targets. Track work daily, and raise risks and blockers as soon as they appear, not at the deadline. Basic Qualifications AI engineering Expert daily use of AI coding tools (Claude Code, Cursor, Copilot or similar), including agentic, multi-file and multi-step development. Prompt and context engineering: system prompts, structured outputs, few-shot design, managing the context window. LLM application patterns: RAG (chunking, embeddings, vector stores, retrieval tuning), tool use/function calling, agents and multi-agent orchestration, MCP servers and connectors. Evaluation and guardrails: test sets, output validation, hallucination checks, prompt injection and data-leakage defences, human-in-the-loop design. Working knowledge of model selection, latency, token cost and rate-limit trade-offs across the major LLM APIs (Anthropic, OpenAI, Azure OpenAI or similar). Document and data AI: extracting from PDFs, emails, spreadsheets and scanned forms; classification; summarisation. Full-stack engineering Front end: React/TypeScript (or similar), responsive UI, component libraries. Back end: Python (FastAPI/Flask) and/or Node.js, REST/GraphQL APIs, async and background jobs. Data: SQL and NoSQL databases, data modelling, ETL, basic analytics and reporting. Integrations: enterprise APIs, webhooks, OAuth, and platforms such as Microsoft 365/SharePoint, Salesforce, SAP and ServiceNow. Workflow automation: Power Automate, Logic Apps, n8n or similar, and knowing when code beats low-code. Cloud, DevOps and security Cloud deployment on Azure (preferred), AWS or GCP; App Services, containers (Docker), serverless functions. Git, CI/CD pipelines, environment management, secrets management. Authentication and authorisation: SSO, Entra ID/Azure AD, OAuth2/OIDC, role-based access. Secure coding practices, OWASP awareness, and handling sensitive and personal data. Logging, monitoring and alerting for production support. Delivery and business A track record of hitting fixed deadlines with multiple projects running at once. Strong scoping and prioritisation: cutting to a minimum viable release and phasing the rest. Clear communication with non-technical stakeholders, including demos, status updates and expectation management. Experience taking solutions through enterprise security, privacy, legal and change management processes. An independent, ownership-driven style: comfortable being the single person accountable for the solution and the date. Experience 3+ years building and shipping full-stack applications to production. A portfolio or examples of AI-built solutions delivered end to end, including timelines and outcomes. At least one LLM-powered application or agent in production use. Preferred Qualifications Previous FDE, solutions engineering, technical consulting or internal-tools experience. Experience in a regulated industry (e.g. healthcare, life sciences, manufacturing, finance) and familiarity with frameworks such as GDPR, ISO 27001, SOC 2 or GxP. Experience building internal AI platforms, shared skill libraries or reusable agent frameworks. Python data tooling (pandas, notebooks) and basic ML familiarity. Salary Range  $65,000 - $85,000 USD This role is being hired for a Gruve customer. Gruve is unable to provide sponsorship for this role. Candidates must be U.S. Citizens.   ‍ Why Gruve At Gruve, we foster a culture of innovation, collaboration, and continuous learning. We are committed to building a diverse and inclusive workplace where everyone can thrive and contribute their best work. If you’re passionate about technology and eager to make an impact, we’d love to hear from you. Gruve is an equal opportunity employer. We welcome applicants from all backgrounds and thank all who apply; however, only those selected for an interview will be contacted.