Design and implement advanced AI systems that power conversational agents, retrieval-augmented workflows, and voice-based interactions. This role centers on building reliable, low-latency solutions tailored to enterprise needs in regulated industries such as healthcare, finance, government, and telecommunications.
Key Responsibilities
- Develop and deploy production-ready AI services using Python and FastAPI
- Construct and refine retrieval-augmented generation (RAG) pipelines with optimized chunking, embedding, and reranking strategies
- Integrate large language models from providers like OpenAI, Anthropic, and Google, as well as open-source variants
- Design system prompts, apply chain-of-thought reasoning, and enforce structured outputs using function calling or JSON mode
- Implement voice AI capabilities using STT and TTS technologies, including real-time agent frameworks
- Ensure AI components are observable, monitored, and evaluated using frameworks like RAGAS or custom LLM-as-judge pipelines
- Collaborate with backend, frontend, and QA teams to embed AI features into broader product ecosystems
Qualifications
Applicants must hold a bachelor’s degree in Computer Science, Artificial Intelligence, Data Science, or a related field. Proficiency in Python is required, along with experience exposing AI services via FastAPI.
Preferred candidates will have a master’s in AI/ML or relevant certifications, and hands-on experience with LangChain, LlamaIndex, or similar frameworks. Familiarity with vector databases such as Pinecone, Weaviate, or Qdrant is strongly desired. Experience deploying models on GCP or Azure—particularly using Vertex AI or Azure OpenAI—is an asset.
Work Environment
The role operates in agile, sprint-driven cycles, balancing rapid innovation with engineering discipline. Success requires clear communication of model behavior and limitations to non-technical partners, proactive definition of evaluation metrics, and continuous learning amid evolving AI advancements. The ideal candidate combines technical depth with a quality-first approach and thrives in collaborative, cross-functional settings.
