Forward Deployed Engineer

1. ROLE DETAILS

Title: AI Engineer

Department: Service Delivery

Reports to: AI Solutions Architect – Lead

Direct reports: None

Location: Denver or Grand Junction, CO (hybrid-first); Remote for the right candidate

FLSA status: Exempt

Effective date: 28OCT2026

2. MISSION

Forward Deployed Engineers work inside customer teams to take hard, ambiguous business problems to working production solutions, acting as the customer’s technical owner from discovery and scoping through build, rollout and handoff. The role carries EggNest’s expansion from AI platform services into Advanced AI Solutions: custom agents, custom connectors, MCP servers and embedded engineering across Glean, Claude and OpenAI. The company gets production solutions customers use and trust, reusable assets that make every next engagement faster, and the foundation of its FDE practice.

3. KEY RESPONSIBILITIES

1. Embeds with customer teams, understands the workflow behind each request, and turns it into a scoped plan with clear acceptance criteria.
2. Builds and ships production agents, agentic workflows, custom connectors, MCP servers and integrations across customer systems, with permissions and governance preserved.
3. Works with customer data teams on governed data access, semantic layers and validation against existing reports.
4. Joins pre-sale technical discovery and gives a clear go, reshape or decline recommendation, including when a platform cannot do what is being asked.
5. Sees each engagement through testing, customer sign-off, release, documentation and training, then supports what they shipped.
6. Measures and shows real customer impact with system data and customer quotes.
7. Turns what they learn in the field into reusable templates, patterns and playbooks that make the next engagement faster.
8. Coaches customer champions and engineers and contributes to hiring and mentoring as the team grows.
9. Front-end application engineering - Builds usable, production-quality interfaces for agentic applications and internal tools using modern web frameworks, TypeScript/JavaScript, APIs and component-based UI patterns. Handles authentication, permissions, loading and error states, streaming responses, responsive design, accessibility, and testing so customers can reliably use what is built.

4. KEY OUTCOMES

1. Ships the first customer solution to production with customer acceptance. Outcome measured by first customer solution live and accepted within 90 days of start. System of record: GitHub / Jira, customer acceptance form
2. Owns a complex engagement end to end.

Outcome measured by

leading one complex engagement from discovery through sign-off, release and handoff within 6 months of start. Project plan, customer acceptance form

3. Contributes reusable assets to the FDE practice. Outcome measured by at least 2 reusable templates, patterns or playbooks contributed within 6 months of start. System of record: GitHub, internal docs
4. Shows measurable customer impact for each solution shipped Impact summary with system data and customer quotes delivered at handoff for every shipped solution. Outcome is reviewed quarterly. System of record: usage dashboards, handoff package

5. QUALIFICATIONS

Required

• 5+ years of engineering or technical deployment experience that includes customer-facing work (forward deployed engineering, solutions engineering, professional services or consulting).
• Strong production-grade Python and/or TypeScript/JavaScript.
• Experience building and deploying LLM-powered systems in production, including prompt and instruction design, tool use, retrieval and evaluation.
• Experience integrating enterprise systems through APIs: authentication (OAuth, service accounts), permissions, pagination, rate limits and incremental sync.
• Working knowledge of SQL, a major cloud (AWS or GCP), Git and CI/CD.
• A record of scoping and delivering complex projects in fast-moving, ambiguous environments, through UAT and written customer acceptance.
• Clear communication with executives, business users and engineers, and the judgment to say what will and will not work.
• Experience building MCP servers, custom connectors, agent skills or sub-agents.

Preferred

• Experience with Glean, Claude or OpenAI platforms and AI coding tools such as Claude Code or Codex.
• Experience with data warehouses and semantic layers (for example Snowflake or Tableau).
• Experience in regulated industries such as financial services or healthcare.

6. COMPETENCIES

Job-Specific Competencies: Technical

Production LLM and agent engineering

• Designs, implements and iterates on production LLM systems using prompts, instructions, tool calling, retrieval, structured outputs, memory and multi-step workflows. Establishes evaluation sets and acceptance thresholds, and improves quality based on measured results rather than demos or subjective feedback.

Agent architecture and orchestration

• Chooses the right architecture for a problem—including a single agent, multi-agent workflow, deterministic automation or conventional software—and defines clear boundaries between reasoning, tools, data access and business logic. Designs for failure handling, retries, human review and graceful degradation.

Enterprise integration and connector engineering

• Builds reliable integrations with customer systems using REST APIs, webhooks, SDKs, databases and MCP servers. Implements authentication, authorization, permissions, pagination, rate limits, retries, error handling, incremental sync and schema evolution without weakening the customer’s governance model.

Data engineering and semantic validation

• Uses SQL and data modeling to understand source systems, joins, business definitions and data quality issues. Works with warehouses, semantic layers and reporting tools to validate that agent outputs reconcile with the customer’s existing reports and operational systems.

Production software engineering

• Writes maintainable, testable Python and/or TypeScript/JavaScript. Applies sound software design, typed interfaces, configuration management, dependency management, code review, automated testing and documentation to systems that other engineers can operate and extend.

Cloud and release engineering

• Uses AWS or GCP, Git and CI/CD to deliver repeatable environments and releases. Manages secrets and configuration appropriately, separates development from production, supports rollback, and leaves behind deployment instructions that enable customer or internal teams to operate the solution.

Reliability, observability and operations

• Implements production solutions with logs, metrics, traces and usage monitoring. Defines operational dashboards and alerts, investigates failures across the model, application and integration layers, and establishes practical support, incident-response and maintenance procedures.

Security, privacy and responsible AI

• Designs solutions around least-privilege access, data classification, tenant isolation, prompt-injection resistance, auditability and appropriate handling of sensitive data. Identifies security, privacy and compliance risks early and documents the controls required for production approval.

Technical discovery and solution architecture

• Converts ambiguous customer problems into workflows, system requirements, data flows, integration boundaries, acceptance criteria and an implementation plan. Evaluates feasibility, identifies dependencies and risks, and recommends whether to proceed, reshape the request or decline it.

Production validation and customer handoff

• Leads technical testing, UAT and production readiness reviews; validates outputs against system data and customer reports; resolves defects through acceptance; and produces documentation, runbooks, training materials and handoff artifacts that allow the customer to operate what was built

Job-Specific Competencies: Behavioral

End-to-end ownership

• Acts as the customer’s technical owner from discovery through signoff, handoff and support, and drives the next step without being asked.

Candid technical judgment

• Gives a clear go, reshape or decline recommendation, and says plainly when a platform cannot do what is being asked.

Customer communication and coaching

• Explains trade-offs to executives, business users and engineers, and leaves customer champions able to run what was built.

7. WORK ENVIRONMENT

Hybrid, based in Denver or Grand Junction, CO, or remote within the U.S. Must be eligible to work in the United States, visa sponsorship is not available with Eggnest.ai Shall be embedded with customer teams and working closely with the AI Solutions Architect – Lead and Team Osprey. Occasional customer on-site sessions as required. Target start date of 01DEC2026. Standard office and computer-based physical requirements.

8. COMPENSATION & BENEFITS

• Pay range: Aligned to Market
• Variable pay: Employee Equity Plan
• Benefits: Medical, dental and vision; 401(k); paid time off; paid holidays; FSA/HSA
• Application deadline: Applications accepted on an ongoing basis

Submit your resume and relevant project or portfolio links via the EggNest.ai Careers page