Forward Deployed Engineer (FDE) – Applied AI

Forward Deployed Engineer (FDE) – Applied AI

Work Arrangement: Onsite
Start Date: Immediate
Travel: Up to 50%

Job Summary

We are seeking an experiencedForward Deployed Engineer (FDE) to serve as a leadAgent Engineer for complex customer-facing AI initiatives. The ideal candidate will transform conversational AI prototypes intoproduction-ready, scalable, secure, and high-performing AI solutions.

This role requires strong expertise insoftware engineering, Conversational AI, machine learning operations, cloud infrastructure, and enterprise integrations, along with the ability to work directly with customer engineering teams.

Key Responsibilities

• Lead the development of complexConversational AI and CX applications, transitioning prototypes into production-grade agentic workflows.

• Design and implementmulti-agent systems, agentic workflows, and MCP-based solutions.

• Architect conversational solutions integrating AI platforms withAPIs, legacy systems, enterprise data sources, and security infrastructure.

• BuildAI evaluation pipelines and observability frameworks to monitor and optimize agent performance.

• Optimize reasoning loops, tool selection, latency, reliability, and production security.

• Identify recurring technical challenges and developreusable modules, frameworks, and engineering solutions.

• Collaborate closely with customer engineering teams to implement scalable development and deployment practices.

• Troubleshoot and resolve complex issues acrossAI agents, microservices, APIs, networking, and cloud infrastructure.

• Drive solutions from initial prototype through production deployment and long-term adoption.

• Translate customer requirements into scalable technical architectures and measurable business outcomes.

Required Qualifications

• Bachelor's degree inComputer Science, Engineering, or a related technical field, or equivalent practical experience.

• 5+ years of software development experience using Python or similar programming languages.

• Experience architecting and deployingAI systems on cloud platforms, preferably GCP.

• Hands-on experience withTerraform or similar Infrastructure-as-Code tools.

• Experience buildingfull-stack applications integrated with enterprise IT environments.

• Experience working oncustomer-facing technical projects and production deployments.

• Strong understanding ofcloud infrastructure, APIs, microservices, networking, and security.

Preferred Qualifications

• Master's or PhD inAI, Computer Science, or a related field.

• Experience implementingmulti-agent AI systems using approaches such as ReAct and self-reflection.

• Experience debugging agent logic and optimizingtool selection and agent performance.

• Experience tracing conversation IDs across microservices to troubleshoot production issues.

• Experience connecting AI agents toenterprise knowledge bases and implementingRAG solutions.

• Knowledge of RAG chunking and techniques for reducing hallucinations.

• Experience troubleshootinghigh-traffic production systems during critical events.

• Strong customer-facing communication and technical leadership skills.

• Willingness and ability totravel up to 50%.

Key Skills

• Python

• Conversational AI

• Agentic AI / AI Agents

• Multi-Agent Systems

• MCP Servers

• RAG

• Machine Learning Operations (MLOps)

• GCP / Cloud Architecture

• Terraform / Infrastructure as Code

• APIs & Microservices

• Enterprise Integrations

• AI Evaluation & Observability

• Production Troubleshooting

• Networking & Security

• Full-Stack Development

• Customer-Facing Engineering

• Technical Leadership