Join a dynamic team focused on driving innovation and growth through advanced enterprise technology. We specialize in building cutting-edge AI capabilities that leverage Large Language Models (LLMs), retrieval augmented generation (RAG), and applied machine learning. Our work involves developing and deploying production-grade services for a wide range of applications, from structured data generation to complex analytics.

Develop sophisticated AI solutions incorporating LLM orchestration, retrieval techniques, and applied ML. Implement end-to-end production services for structured generation, extraction, classification, ranking, and analytics. Design and integrate LLM workflows, including prompting, function/tool calling, and agentic steps, with hybrid RAG queries, grounding verification, and citations. Build ML models for classification, extraction, reranking, and forecasting, ensuring robust evaluation. Create APIs for application integration and develop automated quality, grounding, latency, and cost checks through telemetry.

A Bachelor’s or Master’s degree in a relevant field is required. Significant experience, 6+ years, in Python (FastAPI, Pydantic, Pandas/Polars) and LLM frameworks (LangChain/Semantic Kernel) with a focus on function calling and structured outputs is essential. Proficiency with cloud-based model hosting on AWS/GCP/Azure (SageMaker/Vertex AI/Azure ML) and experience with embeddings/vector search are necessary. Familiarity with programmatic document generation (python-pptx, python-docx, reportlab) and diagramming tools (Mermaid/Graphviz) is important. Practical experience in machine learning for extraction/classification, evaluation methodologies, and productionization patterns is also a key requirement.