Forward Deployed Engineer (FDE) – Applied AI

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

Job Summary

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

This role requires strong expertise in software 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 complex Conversational AI and CX applications, transitioning prototypes into production-grade agentic workflows.

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

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

• Build AI 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 develop reusable modules, frameworks, and engineering solutions.

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

• Troubleshoot and resolve complex issues across AI 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 in Computer 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 deploying AI systems on cloud platforms, preferably GCP.

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

• Experience building full-stack applications integrated with enterprise IT environments.

• Experience working on customer-facing technical projects and production deployments.

• Strong understanding of cloud infrastructure, APIs, microservices, networking, and security.

Preferred Qualifications

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

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

• Experience debugging agent logic and optimizing tool selection and agent performance.

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

• Experience connecting AI agents to enterprise knowledge bases and implementing RAG solutions.

• Knowledge of RAG chunking and techniques for reducing hallucinations.

• Experience troubleshooting high-traffic production systems during critical events.

• Strong customer-facing communication and technical leadership skills.

• Willingness and ability to travel 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