Forward Deployed Engineer

Clutch

1d•Remote

About The Position

As a Forward Deployed Engineer at Clutch, you will be a key member of an agent-specific engineering team, responsible for taking AI agents from the 'sold' stage to 'live and performing' at a credit union. This involves participating in discovery sessions, building integrations with core banking and loan systems, authoring and tuning agent behavior, conducting live tests with staff, and supporting the agent through go-live and initial production weeks. This is a senior engineering role focused on writing production code, making customer-facing judgment calls, and owning the outcome. Your field experience will directly inform product development, influencing defaults, playbooks, and platform capabilities for future agents. You will work closely with AI Operations Managers, who handle the broader implementation, configuration, and ongoing success at multiple credit unions once the agent is defined and live.

Requirements

5+ years of software engineering experience in a fast-paced environment, preferably in SaaS and/or Fintech.
Senior TypeScript and Node.js backend experience in a large codebase (NestJS, CQRS, schema-validated boundaries, dependency injection).
Integration and API engineering skills: secure service-to-service endpoints, third-party APIs, webhooks.
Patience to work with legacy banking systems that were not designed for integration.
Security and auth judgment: OAuth and machine-to-machine auth, tenant-scoped access, secrets handling, no PII in logs.
Customer presence: ability to recommend solutions and justify them, including saying 'no' when appropriate, and making and owning decisions in front of customers.
Code-quality judgment under deadline pressure: ability to take on debt deliberately, name it, and pay it down.
Willingness to travel approximately 20% on average, with potential one- to two-week stretches for kickoffs and go-lives.
Based in the US, able to travel on short notice.
Genuine appetite for LLM agents: eval discipline for non-deterministic systems, reading a system prompt like code, understanding that some decisions must never reach the model.
Curiosity plus shipped work is sufficient; research depth is not required.

Nice To Haves

Voice and telephony experience (LiveKit, Twilio)
Temporal or event-driven orchestration experience
Python experience
Core banking or LOS integration experience
Credit union or banking domain knowledge

Responsibilities

Ship production changes to live agents through the team's review process.
Explain the end-to-end flow of a member's call through the Agents Platform.
Deeply learn one agent, including its system prompt, tool contracts, orchestration triggers, compliance gates, and implementation process.
Join at least one credit union implementation as the second engineer, including live testing sessions.
Map areas where the current implementation process loses time and identify opportunities for defaults or tools to improve efficiency.
Own the technical side of one credit union implementation end-to-end: core and LOS integration, agent configuration, testing, go-live, and initial production weeks.
Run the eval and tuning loop for your agent (golden transcripts, rubric judges, regression suite) and independently change its behavior.
Complete at least two on-site visits and translate field learnings into product decisions with the pod lead and PM.
Contribute at least one reusable capability back to the Agents Platform.
Take a net-new agent from sold to live at its first credit union, demonstrating data-backed results.
Become the go-to engineer for credit union staff when their deployment needs changes.
Write the implementation playbook for your agent to a standard where AI Ops can manage subsequent credit union implementations without your direct involvement.
Shape the development of future agents based on field observations of current agent performance and limitations.