Senior AI Engineer (Voice & Conversational Systems)

We are looking for a Senior AI Engineer with hands-on experience in building production-grade conversational AI systems, with a strong focus on voice bots and contact center solutions.

This is a voice-first role focused on real-time conversational systems — not a general backend or “LLM-only” development position.

The successful candidate will help design and build advanced AI-driven voice systems that support live call environments and enhance real-time decision-making processes

Key Responsibilities:

• Lead technical design sessions and define architecture for voice and AI-based systems

• Drive architectural decisions for scalable, low-latency conversational platforms

• Mentor and support mid/junior engineers, enforcing best practices and coding standards

• Collaborate with product and business stakeholders to shape delivery roadmaps

• Own complex problem-solving in areas such as call flow optimization, latency reduction, and voice agent accuracy

• Ensure security, compliance, and reliability in customer-facing systems

• Build and maintain AI agents operating in event-driven and real-time environments

• Participate in coding, testing, debugging, and production support.

Required Skills & Experience:

• 6+ years of commercial experience with Python, building scalable production systems

• Strong expertise with backend frameworks such as Django, FastAPI, or Flask

• Proven experience integrating LLM APIs into live applications

• Hands-on experience with Amazon Connect and Amazon Lex (or comparable enterprise conversational platforms)

• Experience building enterprise-grade voice bots and contact center integrations

• Strong understanding of real-time system constraints and telephony integrations

• Expertise in SQL/NoSQL data modeling, query optimization, and scaling systems for conversational workloads

• Experience with CI/CD pipelines, Infrastructure as Code (Terraform or CloudFormation), Docker, Kubernetes, and monitoring tools.

Nice to Have:

• Recent hands-on experience with generative AI systems in production

• Practical knowledge of testing and evaluating AI agents

• Experience with model fine-tuning

• Strong understanding of scalable system architecture (microservices, API orchestration, event-driven design)

• Experience integrating STT (Speech-to-Text), TTS (Text-to-Speech), and NLP services into user-facing platforms

• Flexibility working with different LLM models and frameworks