Role - Lead Backend Engineer – Voice AI Location: Bengaluru Work mode: 5 days/week, Work from Office Experience: 5–8 years MUST HAVE - Voice AI OR VoiceBot AND Python The Role We are looking for a hands-on Lead Backend Engineer – Voice AI to build and own the backend foundations of our Voice AI product. This is a high-ownership, 0 to 1 role. You will work closely with Product, Design, AI/ML, and Engineering teams to turn ambiguous problem statements into reliable, delightful, and scalable customer experiences.

You will influence both product direction and technical architecture while building systems that power real-time, human-like AI conversations. What You’ll Do ● Lead the design, development, and evolution of backend systems that power real-time Voice AI experiences. ● Build reliable, low-latency services for telephony, audio streaming, conversation orchestration, session management, and post-call workflows. ● Develop and operate Voice AI integrations using platforms such as LiveKit, Vapi, Twilio, WebRTC, or similar technologies. ● Integrate speech-to-text, text-to-speech, LLMs, retrieval systems, and AI evaluation pipelines into robust production workflows. ● Build agentic and conversational workflows using tools such as LangChain, LangGraph, or equivalent frameworks. ● Design scalable APIs, event-driven workflows, data models, background jobs, and fault-tolerant systems. ● Own backend services built with Python, FastAPI, PostgreSQL, Redis, queues, and cloud infrastructure. ● Lead, mentor, and grow a high-performing team of talented engineers;

create clarity, set a high execution bar, and enable the team to deliver ambitious outcomes in a fast-moving environment. ● Partner with Product and Design to identify customer problems, define requirements, run experiments, and ship end-to-end features. ● Make thoughtful trade-offs across speed, product experience, latency, reliability, security, scalability, and cost.



● Establish strong observability across the platform, including logging, monitoring, alerting, tracing, and meaningful product/quality metrics. ● Define and improve metrics such as call success rate, latency, conversation completion, AI quality, and user satisfaction. ● Raise the engineering bar through architecture reviews, code reviews, documentation, and mentorship. What We’re Looking For ● 5–8 years of backend engineering experience, including ownership of customer-facing production systems. ● Strong proficiency in Python and backend frameworks such as FastAPI. ● Strong experience with relational databases, especially PostgreSQL, along with caching and asynchronous processing using tools such as Redis, queues, and background workers. ● Experience designing scalable APIs, distributed systems, asynchronous workflows, and event-driven architectures. ● Hands-on experience with Voice AI, conversational AI, telephony, WebRTC, real-time communications, or audio/video streaming systems. ● Experience with platforms or tools such as LiveKit, Vapi, Twilio, or similar Voice AI and communications technologies. ● Practical experience building LLM-powered applications, including prompt orchestration, tool calling, RAG, structured outputs, and AI evaluation/monitoring. ● Experience with LangChain, LangGraph, or comparable agentic workflow frameworks. ● Familiarity with cloud infrastructure, Docker, CI/CD, monitoring, logging, tracing, and production incident debugging. ● Strong product mindset: you care deeply about user experience, customer outcomes, and business impact, not just clean code. ● Ability to thrive in ambiguity, independently define a path forward, and take ideas from zero to production. ● Strong communication skills and the ability to work effectively across Engineering, Product, Design, and AI/ML teams. ● Demonstrated experience leading or managing a strong engineering team, including technical direction, prioritization, mentoring, performance coaching, and creating an workplace of high ownership and accountability.

📌 Lead Backend Engineer - Voice Ai (Yelahanka)
🏢 Qrata
📍 Yelahanka