Job Description – AI/ML Engineer (LLM & Voice AI)
Job Title: AI/ML Engineer (LLM & Voice AI)
Experience: AI [min 3 years exp]
Location: Gurgaon (Preferred) / Bangalore (Secondary Option)
Work Mode: Work from Office
Notice Period: Immediate Joiners / Up to 20 Days Preferred
About the Role
We are looking for a highly skilled AI/ML Engineer to build next-generation AI-powered, multilingual, omnichannel communication solutions. This role is ideal for professionals with hands-on experience in Voice Bot Development, Large Language Models (LLMs), NLP, Retrieval-Augmented Generation (RAG), Python, and FastAPI.
You will work on developing intelligent AI solutions including voice assistants, speech recognition, agent assist systems, summarization, sentiment analysis, and scalable AI services for enterprise applications.
Mandatory Skills (Must Have)
Candidates must possess hands-on experience in the following technologies:
- Voice Bot Development – Minimum 1–2 years of relevant experience (Mandatory)
- Large Language Models (LLMs) – Mandatory
- Natural Language Processing (NLP) – Mandatory
- Retrieval-Augmented Generation (RAG) – Mandatory
- FastAPI – Mandatory
- Python – Strong hands-on development experience
- Experience with LangChain, Whisper/STT, or Hugging Face frameworks
- Experience in building and deploying AI inference APIs and microservices
- Knowledge of REST APIs, Docker, Kubernetes, Redis, and Kafka is highly preferred
Key Responsibilities AI/ML & LLM Development
- Design, develop, and deploy AI-powered Voice Bot solutions.
- Build and optimize LLM-based applications using GPT, LangChain, Hugging Face, and RAG architectures.
- Develop intelligent features such as:
- Conversation Summarization
- Sentiment Analysis
- Auto-Disposition
- Escalation Tagging
- Emotion Detection
- Fine-tune and evaluate speech and language models including Whisper/STT for multilingual Indian languages.
- Implement prompt engineering and Retrieval-Augmented Generation (RAG) pipelines.
- Develop real-time AI inference services using Python and FastAPI.
- Optimize AI model performance for low latency and high scalability.
Backend & Data Engineering
- Build scalable APIs and AI microservices using FastAPI.
- Develop secure and high-performance data pipelines.
- Work with PostgreSQL, Redis, Kafka/RabbitMQ for real-time processing.
- Design ETL/ELT workflows supporting analytics and AI feedback loops.
- Ensure compliance with data security and privacy standards.
Deployment & Infrastructure
- Containerize AI applications using Docker.
- Deploy production workloads on Kubernetes/K3s.
- Build CI/CD pipelines for automated deployment.
- Monitor AI model performance and continuously improve production systems.
Collaboration
- Collaborate with Product, Engineering, and UX teams to deliver AI-driven features.
- Mentor junior AI/ML engineers and promote engineering best practices.
- Participate in AI architecture, roadmap planning, and technology decisions.
Pay: ₹100,000.00 - ₹180,000.00 per month
Education:
Experience:
- Voice bot development: 1 year (Preferred)
- LLM,NLP, RAG, FastAPI.: 2 years (Preferred)
Work Location: In person
