Accepting Applications
Full-time
On-site
Posted 1 hour, 47 minutes ago
0 views
0 applications
Job Description
Role Overview:
We are seeking a Senior AI Engineer to architect and build a high\-performance, custom Voice AI infrastructure. This role focuses on developing an end\-to\-end real\-time audio processing pipeline and an intelligent NLP engine capable of synthesizing complex regulatory data into actionable insights with sub\-second latency.
Key Responsibilities:
\- Custom Voice Infrastructure: Develop a proprietary, low\-latency audio pipeline integrating Speech\-to\-Text (STT), Large Language Models (LLMs), and Text\-to\-Speech (TTS).
\- Intelligent Data Parsing: Architect agentic workflows to ingest complex documentation and translate technical/legal jargon into plain\-language summaries.
\- Real\-time Audio Streaming: Manage full\-duplex audio transmission using WebSockets and WebRTC to achieve human\-like conversational responsiveness.
\- Automated Information Retrieval: Build scalable scrapers and API consumers to monitor high\-frequency data sources and public registries for real\-time updates.
\- Advanced RAG Systems: Implement sophisticated Retrieval\-Augmented Generation (RAG) using Vector Databases to provide the AI with deep contextual awareness.
Technical Requirements:
\- Programming: Expert\-level Python; experience with asynchronous programming and high\-concurrency systems.
\- NLP \& AI: Proven experience with LangChain, LlamaIndex, and fine\-tuning open\-source LLMs.
\- Speech Processing: Experience with real\-time transcription (STT) and neural speech synthesis (TTS) engines.
\- Data Systems: Proficiency with Vector DBs (e.g., Pinecone, Milvus) and SQL/NoSQL databases.
\- Protocols: Strong understanding of WebSockets, WebRTC, and real\-time data streaming.
Location: DHA Phase 6, Karachi.
Shift: Morning.
Login to Apply
Don't have an account? Register