SDE I - AI

We are looking for an AI Engineer - SDE I with strong software engineering fundamentals and hands-on exposure to AI/LLM and conversational or voice-based systems. You will work on backend services, LLM integrations, conversation orchestration, and real-time systems where latency, scalability, reliability, and concurrency are critical.

Responsibilities:

• Build and maintain production-grade backend services using Python; Go is a plus.
• Develop and integrate LLM-powered workflows, including prompt engineering and structured outputs.
• Optimize AI workflows for latency, reliability, and real-time workloads.
• Work on voice, telephony, streaming, and conversational AI systems.
• Develop well-tested, observable, and maintainable production code.
• Participate in code reviews, debugging, incident resolution, and technical ownership.
• Contribute to CI/CD, containerization, and deployment practices.
• Work with real-time systems where concurrency and performance are important.

Requirements:

• Strong programming fundamentals, with Python preferred.
• Experience building and shipping production-grade software.
• Good understanding of Git, testing, debugging, code reviews, and clean architecture.
• Hands-on experience with LLM APIs, prompt engineering, structured outputs, and AI application development.
• Experience with voice AI / conversational AI / speech / real-time systems.
• Exposure to technologies such as ASR, TTS, telephony, streaming audio, or similar systems.
• Comfortable using AI coding tools such as Claude or GitHub Copilot.
• Ability to take ownership of problems and work in a fast-paced environment.

Good to Have:

• Microservices, gRPC, distributed systems.
• Go or asynchronous Python.
• High-concurrency backend development.
• GCP / AWS, Docker, CI/CD, or DevOps.
• Exposure to multilingual NLP.
• Experience building conversational or voice-based products.