Job Location
Gurugram, Haryana (On-site / Hybrid model). Only relevant experience of 6-12 years kindly apply
Job Summary
A high-growth, cutting-edge automation and conversational intelligence systems provider is seeking an exceptional Principal AI/ML Engineer to lead the architecture, design, and deployment of next-generation enterprise voice applications. The ideal candidate must have 6 to 12 years of hands-on software engineering and artificial intelligence experience, with a proven track record of shipping production-grade real-time audio systems. You will serve as the core technical authority, orchestrating state-of-the-art Multi-Agent workflows and low-latency voice bot infrastructures that process massive volumes of concurrent transactional voice calls.Core Responsibilities
- Architect, build, and optimize high-performance, real-time AI Voice Support Agents, integrating live audio stream processing pipelines natively with enterprise telephony control systems and cloud API gateways.
- Design and execute advanced Agentic AI architectures, implementing complex multi-agent task decomposition, recursive reasoning networks, and persistent context preservation to handle unstructured user intents.
- Construct and scale high-concurrency conversational Retrieval-Augmented Generation (RAG) frameworks, integrating vector search databases and customized semantic routing components to minimize conversational response latency.
- Conduct deep algorithmic model tuning, fine-tuning open-source Large Language Models (LLMs) and Speech-to-Text (STT) or Text-to-Speech (TTS) models using advanced optimization frameworks to maximize context accuracy.
- Establish robust system testing pipelines, model evaluation metrics, and strict guardrails to eliminate hallucinations, ensure high-fidelity audio outputs, and maintain real-time service stability.
- Direct cross-functional collaboration between backend platform engineering, product development, and infrastructure teams, while continuously driving agile software development sprint deliverables.
Required Experience and Qualifications
- Total Experience: Non-negotiable 6 to 12 years of professional, full-time engineering tenure with a substantial portion explicitly focused on deploying AI/ML solutions in production.
- Core Technical Stack: Deep technical mastery of Python backend programming, automated data pipelines, distributed microservices, and asynchronous event-driven architectures.
- Voice & Conversational Tech: Verbatim hands-on experience building voice bot interfaces, configuring intent classification frameworks, managing real-time audio streaming inputs, or integrating telecommunication systems.
- Agentic & LLM Tooling: Practical proficiency building long-running workflow automation systems utilizing advanced prompt engineering, custom function calling layers, and LangChain or LangGraph frameworks.
- Infrastructure: Solid experience working with containerization tools, version control frameworks, continuous integration pipelines (CI/CD), and high-availability cloud endpoints.
- Academic Background: Bachelor's or Master’s degree in Computer Science Engineering, Artificial Intelligence, Data Science, or an equivalent technical field.
What We Offer
- Top-tier compensation structure optimized for principal-tier engineering specialists.
- Opportunity to spearhead greenfield architecture for a pioneering, high-scale digital transformation enterprise.
- Highly innovative, tech-first workplace with massive operational scaling autonomy.
Pay: ₹1,600,000.00 - ₹1,706,294.96 per year
Benefits:
- Flexible schedule
- Leave encashment
- Paid sick time
- Paid time off
- Provident Fund
Work Location: In person
