What you’ll do:
* Architect and deploy AI-first systems that automate complex real-world workflows across voice, text, and vision.
* Work directly with LLMs and multimodal models, expanding their integration into production systems.
* Build and fine-tune RAG pipelines, agent frameworks, and orchestration systems that combine reasoning, retrieval, and action.
* Experiment with prompt engineering, model fine-tuning, LLM APIs, and vision-language models to address structured data extraction challenges.
* Collaborate cross-functionally to move prototypes from whiteboard to production within weeks.
You might be a fit if you’ve:
* Shipped AI-powered products using LLMs, embeddings, or multimodal systems.
* Worked with OpenAI, Anthropic, Hugging Face, or internal LLM APIs at scale.
* A deep understanding of RAG, agentic workflows, function calling, and LLM performance evaluation.
* Strong experience with Python, TypeScript, and modern frameworks such as FastAPI, Next.js, LangChain, or LlamaIndex.
* Hands-on experience with vector stores, embedding pipelines, and cloud AI stacks (AWS, GCP, or Azure).
* Experience in fast-paced 0→1 environments with rapid iteration and ownership.
* Bonus: exposure to OCR, computer vision, document parsing, or healthcare automation use cases.
