Forward Deployed Engineer

Build on the Enterprise GPT Platform s

Design and ship agents and multi-step workflows using Glean, Claude, and other GPT platforms and applying platform tools such as Agent Builder, actions, MCP tools, and adjacent automation s (e.g., n8n, Zapier , Make)

Apply AI solution patterns such as retrieval-augmented generation (RAG), workflow orchestration, agent-assisted processes, model integration, API-based automation, and human-in-the-loop review

Integrate & Orchestrate

Create connections to ingest data from enterprise systems like Salesforce, ServiceNow, SharePoint/Teams, email, and internal APIs

Extend platform capabilities through MCP-based integrations and context-aware workflows that improve the usefulness and reach of AI solutions

Implement custom services and integrations, including REST APIs and webhooks, when platform-native patterns or existing automations are not sufficient

Ensure solutions are secure, reliable, observable, and compliant with enterprise standards

Create reusable templates, components, and solution patterns that can be applied across teams and use cases

Identify & Solve Business Friction Points

Proactively surface pain points across business workflows and reimagine them leveraging the best available technology to create impact

Rapidly prototype, validate with real users, and harden MVPs into scalable, production solutions

Partner with stakeholders to prioritize high-impact use cases based on business value, feasibility, risk, and repeatability, with a focus on scalable solutions rather than one-offs

Measure and communicate the value of solutions delivered, including time saved, errors reduced, adoption, reliability, and operational performance

Own LLM Quality, Telemetry & Cost

Apply production LLM practices: prompt and agent design, guardrails, and evaluation

Use test sets, quality metrics, and offline or online evaluation methods to improve solution performance over time

Instrument usage, reliability, and token/credit consumption at the agent and team level

Use data to improve quality and reduce unnecessary spend (context scoping, summarization, caching, model choice)