Forward Deployed Engineer

We are looking for a hands-on Forward Deployed Engineer (FDE) with strong Python and Generative AI experience to build, integrate, and deploy AI-powered applications for enterprise customers. In this customer-facing engineering role, you will work on configuring and deploying AI agents, developing prompts and conversation flows, integrating customer systems, and ensuring reliable production deployments. You will collaborate closely with senior FDEs, product, and engineering teams to deliver high-quality AI solutions.

Responsibilities:

• Build, configure, and deploy Voice and In-App AI Agents for customer environments.
• Design, write, and optimise prompts, system instructions, tool calling, and conversation flows for LLM-based agents.
• Implement tools, guardrails, and structured outputs to improve agent performance and reliability.
• Integrate AI agents with customer systems using APIs, webhooks, SDKs, and telephony integrations.
• Handle multilingual conversations, edge cases, and customer-specific workflows.
• Run evaluations to measure and improve agent accuracy, response quality, latency, and conversion.
• Debug production issues and improve application reliability and performance.
• Support customer demos, technical walkthroughs, and deployment discussions.
• Collaborate with senior FDEs, product, and engineering teams to deliver customer deployments.
• Document deployment processes and contribute to reusable technical playbooks.
• Occasionally travel to or work from customer sites to support deployments and ensure smooth operations.

Requirements:

• 2-3 years of experience building and shipping production-grade software applications.
• Strong hands-on experience with Python and software engineering fundamentals.
• Practical experience building LLM/GenAI applications, including prompting, RAG, and tool calling.
• Understanding of prompt engineering for LLM agents, including system prompts, tool usage, and structured outputs.
• Working knowledge of LLM application development and integration.
• Experience with REST APIs, webhooks, and SDK integrations.
• Exposure to cloud platforms, preferably AWS.
• Ability to troubleshoot production issues and understand application reliability and latency fundamentals.
• Strong problem-solving and debugging skills.
• Good written and verbal communication skills, with the ability to interact confidently with customers.
• Experience in Forward Deployed Engineering, Solutions Engineering, Implementation Engineering, or similar customer-facing technical roles.
• Experience deploying LLM/GenAI applications in production or real customer environments.
• Exposure to Voice AI, conversational AI, and telephony integrations.
• Experience working with enterprise customers.
• Ability to independently own technical projects and drive them from setup to production.

Skills

API, Gen AI, LLM, Python, RAG, REST, SDK, Webhooks