Seeking an AI Engineer to support our IVR and Conversational AI platforms, with a strong focus on building LLM powered voice and chat experiences. This role involves designing and developing prompt driven and RAG based AI solutions that enhance customer interactions across IVR channels. The ideal candidate will have hands on experience with large language models, vector databases, and conversational AI frameworks. As this position supports both English and Spanish customer experiences, the candidate must be a native Spanish speaker to ensure high quality prompt design, linguistic accuracy, and culturally aligned conversational flows.
Experience: 10 Plus years.
3+ years of experience in AI / ML development
Strong proficiency in Python
Hands-on experience with LLMs, including:
Prompt engineering
Model evaluation
Retrieval-Augmented Generation (RAG)
Experience working in enterprise or customer-facing systems is a plus
Nice to have Skills: NLP experience related to conversational AI
* Develop and maintain AI solutions for IVR and conversational platforms
* Implement LLM-based workflows including prompt engineering, evaluation, and RAG
* Build knowledge retrieval pipelines to support IVR use cases (FAQs, troubleshooting, account queries)
* Collaborate with IVR, speech, and platform teams to integrate AI models into production systems
* Evaluate model performance for accuracy, latency, and conversational quality
* Assist in continuous improvement of AI-driven voice experiences
* Python / ML: NumPy, Pandas, Scikit-learn
* LLM Frameworks: LangChain, LlamaIndex, Hugging Face Transformers
* Vector Databases: FAISS, Chroma, Pinecone, Qdrant
* NLP (Good to Have): spaCy, NLTK, Sentence-Transformers
* LLM Evaluation: TruLens, DeepEval, OpenAI Evals