Domain-Specific Chatbot Engineer

WorkSprout is a deep-tech engineering and design partner across twelve practice areas — TinyML & Edge AI, Custom AI Development, AI Automation & Agents, Data Engineering & Collection, IoT Solutions, Hardware Prototyping, Robotics & Automation, 3D Design & Modeling, Software Development, Growth & DevOps, Branding & Creative Design, and Startup & Product Launch. We deliver systems that work in production, not just in demos.

You will design and deploy domain-specific conversational AI systems that solve real business problems. Your work spans intent recognition, knowledge base integration, and production-grade chatbot infrastructure built on the latest LLM technology.

• Design and fine-tune LLM-based chatbots for specific industry domains
• Build RAG (Retrieval-Augmented Generation) pipelines with vector databases
• Integrate chatbots with REST APIs, CRMs, and enterprise data sources
• Evaluate response quality, hallucination rates, and latency benchmarks
• Deploy and monitor chatbot services on cloud infrastructure
• Collaborate with product teams to define conversation flows and UX

• Proficiency in Python and LLM frameworks (LangChain, LlamaIndex)
• Experience with OpenAI, Anthropic, or open-source LLMs (Llama, Mistral)
• Knowledge of vector stores (Pinecone, Weaviate, ChromaDB)
• REST API development and integration experience
• Strong understanding of prompt engineering and evaluation techniques

• Experience with conversational analytics and A/B testing
• Familiarity with Rasa or Botpress frameworks
• Knowledge of multilingual NLP pipelines

• Work on real-world enterprise AI deployments
• Competitive salary benchmarked to international rates
• Flexible hybrid work arrangement
• Access to latest LLM APIs and compute resources
• Dedicated research and innovation time

* Benefits marked with an asterisk apply to permanent employees only.

If your experience matches the requirements and you are ready to work on production engineering and design challenges, submit your application using the button below. We review every submission personally — no automated screening, no ghosting.