Description

Architect and build scalable LLM, conversational, and voice AI solutions. Own the end-to-end development from prompt engineering to MLOps deployment.

This role is on-site.

Responsibilities

• Design and implement scalable LLM and voice AI architectures using Python, ASR, TTS, and NLP pipelines.
• Build end-to-end AI applications integrating LLMs with enterprise systems (CRM, ticketing) and cloud-native services.
• Create frameworks for conversational flows, prompt engineering, RAG, and context management.
• Implement MLOps practices including CI/CD, model versioning, A/B testing, and governance.
• Set up monitoring for latency, hallucination rates, drift, and model quality; optimize inference costs and token usage.

Required Skills

• 5+ years of experience with Python and AI solution development.
• Strong expertise in LLM architecture, prompt engineering, and RAG.
• Experience with CI/CD pipelines and MLOps tools.
• Knowledge of GCP, Azure, or AWS cloud platforms.
• Proficiency in ASR, TTS, and voice bot engineering.
• Ability to integrate APIs, vector search, and embeddings.
• Experience with enterprise AI governance and security standards.

Preferred Skills

• Experience with Azure OpenAI or specific speech APIs (Azure, Amazon, Google).
• Familiarity with telephony integrations (Twilio, Genesys) and chat platforms (Teams, Slack).

Key Skills

Education

Any Gradute