Description:
We are hiring a Senior LLM & Conversational AI Engineer with strong hands-on experience in building AI chat agents, real-time AI voice agents, LLM-powered systems, and enterprise-grade conversational AI solutions.
This is not an entry-level AI role. We are specifically looking for someone who has already built and deployed serious LLM-based applications, preferably including enterprise-level voice agents, real-time conversational systems, AI assistants, RAG pipelines, and agentic workflows.
The ideal candidate should be technically strong, deeply hands-on with coding, comfortable with old-school software engineering fundamentals, and capable of researching, testing, and implementing the latest advancements in LLMs, speech AI, and conversational AI.
Key Responsibilities:
- Design, develop, and deploy production-grade LLM-based chat and voice agents.
- Build real-time conversational AI systems with low-latency voice interaction flows.
- Integrate Speech-to-Text, Text-to-Speech, voice orchestration, telephony, and real-time streaming technologies.
- Develop AI agents using LLMs, RAG, tool calling, memory, workflow routing, guardrails, and evaluation frameworks.
- Architect scalable AI systems for enterprise and multi-tenant SaaS environments.
- Work with LLM APIs and frameworks such as OpenAI, Anthropic, Gemini, Azure OpenAI, AWS Bedrock, LangChain, LangGraph, LlamaIndex, or similar tools.
- Build and optimize RAG pipelines using vector databases, embeddings, chunking strategies, retrieval logic, and evaluation methods.
- Write clean, scalable, well-structured, and maintainable code.
- Debug complex AI behavior, latency issues, hallucination risks, prompt failures, retrieval problems, and production bugs.
- Stay updated with the latest AI research, LLM frameworks, open-source models, agent architectures, and voice AI technologies.
- Collaborate with product, engineering, and business teams to convert real-world use cases into reliable AI solutions.
Must-Have Qualifications:
- 6+ years of overall professional experience in software engineering, AI engineering, machine learning, or related technical development.
- 3+ years of hands-on professional experience working with LLMs, Generative AI, AI agents, or conversational AI systems.
- Proven experience building and deploying AI chatbots, voice bots, conversational agents, or AI assistants in real-world environments.
- Strong hands-on experience with LLM integration, prompt engineering, function calling, tool calling, RAG, memory, and AI workflow orchestration.
- Experience with real-time or near real-time AI voice systems is strongly required.
- Hands-on experience with Speech-to-Text and Text-to-Speech technologies.
- Strong backend development skills, preferably in Python, FastAPI, Node.js, or similar backend technologies.
- Strong understanding of software engineering fundamentals, APIs, databases, queues, async processing, system design, and scalable backend architecture.
- Experience with vector databases such as Pinecone, Qdrant, Weaviate, Chroma, or similar.
- Experience with cloud platforms such as AWS, Azure, or GCP.
- Ability to read research papers, test new AI approaches, evaluate frameworks, and convert research into working production solutions.
- Strong debugging, problem-solving, and independent execution skills.