Qualifications
Key ResponsibilitiesDesign production-grade prompt architectures for 8B-class models. Develop structured prompts for enterprise tasks such as classification, extraction, reasoning, and summarization. Optimize prompts to enhance accuracy, reduce latency, and improve cost efficiency. Create prompt evaluation frameworks to assess accuracy, hallucination rates, and consistency. Design reusable prompt libraries and templates for enterprise workflows. Formulate strategies for migrating prompts to fine-tuned SLMs. Design and fine-tune LLMs for specific enterprise tasks. Develop SLMs optimized for real-world enterprise deployment. Establish instruction tuning and supervised fine-tuning (SFT) pipelines. Create evaluation datasets and automated benchmarking frameworks. Implement retrieval augmented generation (RAG) pipelines and tool-augmented workflows. Collaborate with speech AI and document AI teams to build multimodal systems. Deploy models in secure private cloud or on-premise environments. Required QualificationsEducation: Master's degree or PhD in Computer Science, AI, Machine Learning, or related field. Experience & Technical Skills:Proven expertise in Prompt Engineering for 7B–13B models, especially 8B models. Experience in designing prompts for enterprise applications.
About the job
About 2070health
2070health builds AI-first automation platforms for the healthcare and insurance sectors. The company focuses on interpreting unstructured conversations, documents, and workflows, aiming for autonomous execution of complex business processes that typically require human input.
Specialties include domain-specific Small Language Models (SLMs) and carefully fine-tuned Large Language Model (LLM) pipelines. These solutions are designed for reliability in regulated, high-stakes settings such as US Healthcare Revenue Cycle Management (RCM).
The technical approach centers on deterministic AI systems, combining prompt engineering, model fine-tuning, and agentic orchestration to support enterprise automation.
Role Overview
2070health seeks a Senior AI Engineer based in Bengaluru, Karnataka. This position calls for deep expertise in prompt engineering, LLM fine-tuning, and SLM development. The engineer will design, train, optimize, and deploy language models tailored to specific domains.
Key work includes developing high-performance prompts for 8B-class models such as LLaMA, Mistral, and Qwen, then evolving these prompts into fine-tuned models that meet production standards for reliability.
Responsibilities also cover designing prompt architectures, instruction schemas, and evaluation pipelines. The goal: ensure models produce accurate, structured, and deterministic outputs that fit enterprise automation workflows.
About 2070health
2070health is at the forefront of AI-driven innovation in the healthcare and insurance industries. Our platform is designed to automate complex processes, ensuring efficiency and reliability. We are committed to developing cutting-edge solutions that transform how businesses operate.