Artificial Intelligence Engineer - LLM Models

We're looking for an AI Engineer with hands-on experience in developing LLM-powered tools, agents, and infrastructure to join our mission.

You'll be working on the core AI systems that power Super Health's multilingual assistant, designed to support doctors and staff across India in 11+ languages. From fine-tuning models to building tool-calling workflows and retrieval systems, you'll help us bring intelligence and automation to every layer of our hospital operations.

Responsibilities :

- Build and deploy end-to-end LLM pipelines: data processing, training, fine-tuning, and fast inference.

- Design multilingual and multimodal systems that span text, voice, and images for clinical use.

- Develop and optimize RAG pipelines, embeddings, and hybrid search using vector databases.

- Extend LLMs with custom tools, real-time APIs, and agent-based tool-calling for operational workflows.

- Run experiments to improve model performance across latency, reliability, and user satisfaction.

- Build internal tools for safety checks, logging, evaluation, and model observability in clinical contexts.

Requirements :

- Proficiency in modern AI/ML libraries (e. g., PyTorch, Hugging Face, LangChain, OpenAI APIs).

- Strong grasp of LLM architecture, fine-tuning, inference, and prompt engineering.

- Experience delivering production-grade AI workflows end-to-end.

- Familiarity with vector databases and orchestration patterns for agents and tool-augmented LLMs.

- Bachelor's in CS, AI/ML, or equivalent hands-on experience.

- Experience with Indian language models or multilingual NLP.

- Contributions to open-source AI projects, papers, or LLM-based demos.

- Knowledge of real-time inference, streaming models, or latency-optimized AI systems.