Job Location: New Delhi

Key Responsibilities

- Design, develop, and deploy applications using Large Language Models (LLMs) and Generative AI technologies.
- Build and optimize Speech-to-Text (STT) , Text-to-Speech (TTS) , and real-time voice AI solutions.
- Develop conversational AI agents, voice bots, and intelligent virtual assistants for enterprise customer interactions.
- Implement Retrieval-Augmented Generation (RAG) , prompt engineering, function calling, and AI agent workflows.
- Integrate LLMs with telephony, contact center platforms, CRM systems, and enterprise applications.
- Optimize speech recognition accuracy, response latency, conversational flow, and multilingual capabilities.
- Develop APIs and backend services for scalable AI-powered applications.
- Evaluate and improve AI model performance, reliability, security, and production readiness.

Required Technical Skills

- Strong programming experience in Python and API development using FastAPI or similar frameworks.
- Hands-on experience with LLMs such as OpenAI GPT, Llama, Claude, Gemini , or other open-source models.
- Experience with AI frameworks such as LangChain, LangGraph, LlamaIndex , or similar technologies.
- Working knowledge of speech technologies such as Whisper, Deepgram, Google Speech-to-Text, Azure Speech , ElevenLabs , or equivalent.
- Understanding of real-time audio streaming, WebSockets, WebRTC , and speech processing pipelines.




- Experience with RAG architectures, embeddings, and vector databases such as FAISS , Pinecone , Chroma , or Milvus .
- Familiarity with telephony technologies, SIP, Twilio, Asterisk, or contact center integrations.
- Familiarity with Docker, Git, REST APIs, and cloud environments ( AWS , Azure , or GCP ).
- Strong problem-solving, debugging, and performance optimization skills.

Good to Have

- Experience developing real-time AI voice agents with low-latency conversational capabilities.
- Understanding of Voice Activity Detection (VAD), interruption handling, turn-taking, and streaming audio.
- Experience with multilingual speech models, particularly Indian languages.
- Knowledge of LLM fine-tuning, model evaluation, guardrails, and AI observability.
- Exposure to enterprise conversational AI and customer experience platforms.

Qualifications

- Bachelor s or Master s degree in Computer Science, Artificial Intelligence, Machine Learning, or a related field.
- Demonstrated experience building and deploying AI/ML applications.
- Robust communication skills and ability to work in a collaborative development environment.

Disclaimer: This job posting has been aggregated from external source. Role details, content, and availability are subject to change. Applicants are advised to confirm the latest information directly on the company website before applying.

📌 LLM / Speech AI Developer (New Delhi)
🏢 consilium software
📍 New Delhi