Urwah Admin

Confiz

<div>We are seeking an exceptional Senior AI Engineer to join our team and drive the development of cutting-edge AI solutions that includes conversational, Agentic AI's. This role focuses on building advanced conversational AI systems, implementation AI Agents across different use cases, implementing sophisticated RAG architectures, and deploying production-grade voice AI applications. The ideal candidate will have deep expertise in LLM technologies and a proven track record of delivering scalable AI solutions.
Key Responsibilities
<ul><li>Design and implement advanced Retrieval-Augmented Generation (RAG) systems with sophisticated chunking strategies, multi-vector retrieval, and hybrid search architectures</li>
<li>Develop and optimize conversational AI agents with complex multi-turn dialogue management and context awareness</li>
<li>Build production-ready voicebot solutions integrating real-time speech processing pipelines</li>
<li>Architect and deploy Text-to-Speech (TTS) and Speech-to-Text (STT) systems with low latency and high accuracy</li>
<li>Design and Deploy PROD grade AI Agents that can scale up for various use cases.</li>
<li>Fine-tune large language models using various techniques.</li>
<li>Optimize model performance through prompt engineering, few-shot learning, and retrieval strategies</li>
<li>Implement evaluation frameworks and metrics for LLM outputs and conversational quality</li>
<li>Develop custom training pipelines for domain adaptation and specialized use cases</li>
<li>Design scalable AI infrastructure supporting real-time inference and high-throughput batch processing</li>
<li>Implement efficient vector databases and semantic search systems (Pinecone, Azure Search)</li>
<li>Build monitoring and observability solutions for AI systems in production</li>
<li>Stay current with latest developments in LLM architectures, RAG techniques, and voice AI technologies</li>
<li>Experiment with emerging models and frameworks to evaluate applicability to business problems</li>
<li>Contribute to technical documentation, best practices, and knowledge sharing within the team</li>
<li>Prototype and validate new AI capabilities through POCs and pilots</li>
</ul>
Required Qualifications
<ul><li>8+ years of software engineering experience with 4+ years focused on AI/ML engineering</li>
<li>Strong proficiency in Python and ML frameworks (PyTorch, TensorFlow)</li>
<li>Master's or PhD in Computer Science, AI/ML, or related technical field</li>
<li>Experience with open-source LLMs (Llama, Mistral, etc.) and local deployment</li>
<li>Knowledge of reinforcement learning from human feedback (RLHF) and DPO</li>
<li>Familiarity with multi-modal AI systems (vision-language models, audio-visual understanding)</li>
<li>Experience with real-time streaming architectures and WebRTC</li>
<li>Published research or contributions to open-source AI projects</li>
<li>Experience with GPU optimization and distributed training</li>
<li>Knowledge of voice biometrics, speaker diarization, or emotion recognition</li>
<li>Background in linguistics, phonetics, or speech processing</li>
<li>Deep hands-on experience with advanced RAG systems:</li>
<li>Multi-stage retrieval architectures (hybrid search, re-ranking)</li>
<li>Embedding models and vector similarity search</li>
<li>Document processing, chunking strategies, and metadata filtering</li>
<li>Query understanding and retrieval optimization</li>
<li>Multi-turn dialogue management</li>
<li>Intent recognition and slot filling</li>
<li>Context tracking and memory management</li>
<li>Integration with LLM APIs (OpenAI, Anthropic, Cohere, etc.)</li>
<li>Production experience with voicebot development:</li>
<li>Real-time audio streaming and processing</li>
<li>Voice activity detection (VAD)</li>
<li>End-to-end latency optimization</li>
<li>Integration of STT, dialogue management, and TTS components</li>
<li>Expertise in TTS and STT technologies:</li>
<li>Modern TTS systems (ElevenLabs, Soniox, Azure Speech)</li>
<li>STT engines ( Deepgram, AssemblyAI)</li>
<li>Audio preprocessing and enhancement</li>
<li>Voice cloning and customization</li>
<li>Strong experience with LLM fine-tuning:</li>
<li>Proficiency with cloud platforms (AWS, GCP, or Azure) and containerization (Docker, Kubernetes)</li>
<li>Experience with MLOps tools and practices (MLflow, Weights &amp; Biases, experiment tracking)</li>
<li>Strong understanding of API design, microservices architecture, and system integration</li>
<li>Knowledge of version control, CI/CD pipelines, and deployment automation</li>
</ul>
We have an amazing team of 700+ individuals working on highly innovative enterprise projects &amp; products. Our customer base includes Fortune 100 retail and CPG companies, leading store chains, fast-growth fintech, and multiple Silicon Valley startups.
What makes Confiz stand out is our focus on processes and culture. Confiz is ISO 9001:2015 (QMS), ISO 27001:2022 (ISMS), ISO 20000-1:2018 (ITSM), ISO 14001:2015 (EMS), ISO 45001:2018 (OHSMS) Certified. We have a vibrant culture of learning via collaboration and making workplace fun.
People who work with us work with cutting-edge technologies while contributing success to the company as well as to themselves.
To know more about Confiz Limited, visit: https://www.linkedin.com/company/confiz-pakistan/</div>

AI Architect

Join Confiz and explore 1   exciting career opportunities. They're hiring for various roles with options for remote or on-site work. Apply today and become part of their innovative team.

Confiz

About Company

AI Architect