| Builds, deploys, and operates LLM-powered agents, chatbots, and generative-AI systems using RAG. Delivers end-to-end AI applications (APIs, data pipelines, and UI integration), designs and iterates prompts/chains/system instructions, and fine-tunes/evaluates foundation models for domain use cases. Establishes CI/CD and orchestration for scalable deployments, monitors and improves quality (accuracy, latency, cost), and implements safety, fairness, governance, observability, and traceability. Creates human-in-the-loop and automated evaluation frameworks (including judge models/scoring), monitors conversational telemetry, and maintains documentation (model cards, playbooks) while mentoring peers. | LLM application engineering (agents, chatbots); RAG frameworks (retrieval, grounding, orchestration); Prompt engineering (prompts, chains, system instructions); Foundation model fine-tuning & evaluation; AI quality measurement (accuracy, latency, cost, safety, fairness) + human evaluation loops; AI observability/telemetry (confidence, latency, escalation, traceability); Vector databases & embeddings pipelines; AI-ready data infrastructure (feature stores, training/inference pipelines); CI/CD & deployment for models in cloud/hybrid; Security, privacy, governance, and compliance for GenAI; Technical documentation (model cards, runbooks) & mentoring. |
Never miss an opportunity! Create an alert based on the job you applied for.
