AI / ML Engineer

Design and develop AI-powered voicebots for inbound and outbound calling use cases • Build and orchestrate agentic workflows using LLMs and external tool integrations • Integrate Speech-to-Text (STT) and Text-to-Speech (TTS) systems for real-time voice interactions • Develop multi-step reasoning pipelines using frameworks like Lang Chain • Implement context management, memory, and conversational state handling • Optimize LLM prompts for accuracy, latency, and token efficiency • Build and expose REST/MCP APIs for AI service integration • Ensure scalability, monitoring, and observability of AI pipelines. Skill Set: • Strong experience with LLMs (OpenAI, open-source models, etc.) and deployment on GPU servers. • Hands-on experience with Lang Chain or similar frameworks (Llama Index, Haystack) • Solid understanding of: • Agentic workflows • Tool calling • RAG (Retrieval-Augmented Generation) pipelines • Expertise in prompt engineering and evaluation techniques • Hands-on experience with Docker and Kubernetes • Understanding of GPU-based inference and optimization (nice to have) • Familiarity with cloud platforms (AWS / GCP / Azure).