Senior

We are looking for a Senior Forward Deployed Engineer with strong backend engineering skills and hands-on experience building and deploying LLM/GenAI-powered applications in production.

In this role, you will work closely with enterprise customers to understand their business requirements, design AI-powered solutions, and take ownership of end-to-end deployments. You will combine software engineering, AI agent development, system integration, and customer-facing problem-solving to deliver scalable solutions in real-world environments.

The ideal candidate should be comfortable working in ambiguous environments, independently owning technical implementations, and interacting with senior enterprise stakeholders.

Responsibilities:

• Own complex, high-impact customer deployments end-to-end, from requirement gathering and solution design to integration, production rollout, and post-deployment optimisation.
• Design, develop, and deploy AI agents for Voice AI and in-app customer-facing workflows.
• Build and optimise LLM-powered applications involving RAG, AI agents, tool calling, and structured outputs.
• Develop and refine system prompts, conversation flows, guardrails, and agent logic to improve response quality and reliability.
• Optimise prompts and conversational experiences for multilingual use cases, edge cases, and real-world customer interactions.
• Lead technical integrations with customer systems using APIs, webhooks, SDKs, and telephony integrations.
• Ensure production reliability, performance, latency optimisation, and monitoring of deployed AI solutions.
• Act as the primary technical point of contact for enterprise customers, leading solution discussions, product demonstrations, and technical workshops.
• Work closely with product and engineering teams to translate customer requirements and implementation feedback into platform improvements.
• Establish deployment standards, technical documentation, and best practices for forward deployment.
• Mentor junior and mid-level engineers and contribute to improving engineering and delivery standards.
• Support customer deployments through occasional travel or on-site engagement as required.

Requirements:

• 4-6 years of experience in backend engineering, software development, or forward-deployed engineering.
• Strong proficiency in Python and backend development.
• Hands-on experience building and deploying LLM/GenAI applications in production.
• Strong understanding of AI agents, RAG, tool calling, and prompt engineering.
• Experience with LLMOps, evaluation frameworks, guardrails, and conversation design.
• Strong knowledge of REST APIs, webhooks, SDK integrations, and asynchronous processing.
• Experience with cloud platforms, preferably AWS.
• Ability to troubleshoot production issues related to latency, performance, and reliability.
• Experience handling enterprise customers and end-to-end technical deployments.
• Excellent communication, problem-solving, and stakeholder management skills.
• BFSI, Fintech, or Insurance domain experience is preferred.
• Ability to independently own projects and translate business requirements into production-ready solutions.

Skills

AI Agents, APIs, AWS, Gen AI, LLM, Prompt Engineering, Python, RAG, Webhooks