Job
Description
Role Overview: You will be responsible for developing multi-agent conversational frameworks with adaptive decision-making capabilities, integrating goal-oriented reasoning and memory components into agents, and building negotiation-capable bots with real-time context adaptation and recursive feedback processing. Additionally, you will fine-tune LLMs/SLMs using proprietary and domain-specific datasets, apply distillation and quantization for efficient deployment on edge devices, and benchmark LLM/SLM performance on server vs. edge environments for real-time use cases. Moreover, you will implement contextual dialogue flows using speech inputs with emotion and intent tracking, deploy advanced Speech-to-Speech (S2S) models for naturalistic voice responses, and work on real-time speaker diarization and multi-turn, multi-party conversation tracking. You will also train and evaluate voice biometric models for secure identity verification, implement anti-spoofing layers to detect deepfakes, replay attacks, and signal tampering, and ensure compliance with voice data privacy and ethical AI guidelines. Furthermore, you will develop frameworks for agents to self-correct and adapt using feedback loops without full retraining and enable low-footprint learning systems on-device to support personalization on the edge. Key Responsibilities: - Design and develop multi-agent conversational frameworks - Integrate goal-oriented reasoning and memory components into agents - Build negotiation-capable bots with real-time context adaptation - Fine-tune LLMs/SLMs using proprietary and domain-specific datasets - Apply distillation and quantization for efficient deployment on edge devices - Benchmark LLM/SLM performance on server vs. edge environments - Implement contextual dialogue flows using speech inputs with emotion and intent tracking - Deploy advanced Speech-to-Speech (S2S) models for naturalistic voice responses - Work on real-time speaker diarization and multi-turn, multi-party conversation tracking - Train and evaluate voice biometric models for secure identity verification - Implement anti-spoofing layers to detect deepfakes, replay attacks, and signal tampering - Develop frameworks for agents to self-correct and adapt using feedback loops - Enable low-footprint learning systems on-device to support personalization on the edge Qualifications Required: - Bachelors/Masters degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field - 3-8 years of experience, with a mix of core software development and AI/ML model engineering - Proven hands-on work with Conversational AI, Generative AI, or Multi-Agent Systems - Strong programming skills in Python, TensorFlow/PyTorch, and model APIs (Hugging Face, LangChain, OpenAI, etc.) - Expertise in STT, TTS, S2S, speaker diarization, and speech emotion recognition - Familiarity with LLM fine-tuning, model optimization (quantization, distillation), RAG pipelines - Understanding of agentic frameworks, cognitive architectures, or belief-desire-intention (BDI) models - Knowledge of Edge AI deployment, low-latency model serving, and privacy-compliant data pipelines Please note that the JD does not contain any additional details about the company.,
