Forward Deployed Engineer - AI Agents

We’re looking for an experienced Forward Deployed Engineer (FDE) to design, build, and deploy AI-powered agents for customer service experiences. This role is an integral part of a global AI initiative aimed at revolutionizing how organizations in industries like finance, healthcare, and commerce operate at scale. 

This is a deeply hands-on, customer-facing engineering role. You’ll sit at the intersection of product, engineering, and customers, rapidly prototyping solutions, deploying them in real-world environments, and iterating based on live feedback. You’ll own the Agent Development Life Cycle (ADLC) end to end—from early pilots through production deployment and continuous iteration. If you thrive in startup environments, enjoy shipping early, and love seeing your work in production quickly, this role is for you.

What you’ll do

Partner closely with customer service teams to understand the workflows, pain points, and success metrics

Design and build agent-based systems that automate and augment customer support experiences (chat, voice, ticketing, internal tooling)

Rapidly prototype, test, and deploy AI agents in customer environments (“fail fast, learn faster”)

Own end-to-end delivery: from initial concept → architecture → implementation → deployment → iteration

Build and deploy RAG-based systems, with a strong emphasis on agent orchestration, tool use, and decision-making

Integrate agents with customer systems (CRMs, ticketing platforms, knowledge bases, internal APIs)

Deploy and operate systems in cloud-native environments (primarily AWS)

Work with backend and frontend components to deliver complete customer-facing solutions

Improve reliability, observability, and performance of deployed agent systems

Act as the technical voice in customer conversations, translating requirements into scalable solutions

What we’re looking for

Core Requirements

Strong experience as a software engineer, solutions engineer, or forward deployed engineer in customer-facing roles

Proven experience deploying AI agents to production (agent frameworks, orchestration, tool calling, memory, workflows)

Solid understanding of Generative AI systems, including:

Retrieval-Augmented Generation (RAG)

Agent architectures and evaluation

Prompting, guardrails, and failure handling

Cloud-native development experience, preferably on AWS

Experience designing and operating production systems (monitoring, scaling, reliability)

Comfort working in fast-moving startup environments with ambiguity and tight feedback loops

Strong communication skills and the ability to work directly with customers

Technology Stack

Languages

Go

Python

TypeScript / React

SQL

Frameworks & Tools

LangChain

LlamaIndex

FastAPI / Flask

Docker

Databases & Search

Vector databases

PostgreSQL (RDBMS)

MongoDB or DynamoDB (NoSQL)

Elasticsearch / OpenSearch

Cloud & Infrastructure

AWS

Infrastructure as Code (Terraform, CloudFormation, CDK or similar)

CI/CD pipelines (GitHub Actions, Jenkins, or similar)

Nice-to-Have / Bonus

Experience with MCP (Model Context Protocol)

Prior experience building customer service or contact-center solutions

Experience integrating with CRMs, ticketing systems, or call center platforms

Background in high-growth startups or early-stage companies

Experience with gRPC

What Success Looks Like

You can take a vague customer problem and ship a working agent quickly

You’ve deployed agents that customers actually use in production

You iterate rapidly based on real-world feedback and metrics

You balance speed with pragmatic engineering discipline

You leave systems better than you found them

Mindset We Value

Startup mentality: bias toward action, ownership, and shipping

Fail fast, learn fast: experiments are encouraged when paired with learning

Customer-obsessed: success is defined by customer outcomes

Builder energy: you enjoy getting your hands dirty across the stack

Some of the benefits you'll enjoy working with us

Direct impact on real customer experiences

Opportunity to shape how AI agents are deployed in the real world

High ownership and visibility

Work on cutting-edge agent architectures in production

Competitive compensation and flexible hybrid work.

Opportunity to work with a multi-cultural and multidisciplinary team of experts

A highly competitive compensation package.

Medical insurance

Come and join our #ParserCommunity. 

Follow us on Linkedin