Staff AI Engineer

Overview

As a Staff AI Engineer, you will define and architect AI capabilities including Generative AI, LLM applications, Agentic AI, RAG, and intelligent automation. You will serve as a technical leader and hands-on engineer, taking AI capabilities from concept to reliable production systems and working with Product, Engineering, Data Science, and healthcare domain experts.

What you'll do

• Design and build scalable, production-grade LLM, Generative AI, and Agentic AI solutions for complex healthcare and medical-practice workflows.
• Lead the architecture and implementation of RAG pipelines, AI agents, orchestration, tool calling, document intelligence, and intelligent automation from prototype through production.
• Establish approaches for LLM evaluation, grounding, guardrails, observability, security, latency, and cost optimization.
• Apply prompt engineering, model selection, fine-tuning, retrieval strategies, and ML techniques to specialty-specific healthcare challenges.
• Define reusable AI engineering patterns, architecture standards, and best practices across AI initiatives.
• Partner with Product, Engineering, Data Science, and domain experts to influence technical direction, make architecture decisions, and drive delivery of AI initiatives.
• Mentor senior and junior engineers, conduct technical design reviews, and raise engineering and AI maturity.
• Help ensure AI solutions are secure, explainable, governable, and appropriate for healthcare, with attention to privacy, compliance, and responsible AI practices.

What you'll need

• 8+ years of experience in AI/ML, Machine Learning, Data Science, or Software Engineering, with significant hands-on experience building production AI systems.
• Deep hands-on experience with LLMs, Generative AI, RAG, prompt engineering, embeddings, vector search, and AI agents.
• Strong proficiency in Python.
• Experience with modern AI/ML frameworks such as PyTorch, Hugging Face, LangChain, LangGraph, LlamaIndex, or equivalent technologies.
• Proven ability to design scalable, reliable AI/ML architectures and translate ambiguous business problems into production-ready technical solutions.
• Strong software engineering fundamentals, including APIs, distributed systems, testing, CI/CD, observability, and production operations.
• Experience deploying AI/ML solutions at scale using AWS or equivalent cloud platforms.
• Experience with platforms such as Databricks, MLflow, SageMaker, or similar technologies.
• Strong understanding of LLM evaluation, hallucination mitigation, grounding, model quality, and AI observability.
• Demonstrated ability to influence architecture and technical direction, mentor engineers, and lead complex initiatives without necessarily having direct people-management responsibility.

Nice to have

• Experience building multi-agent or Agentic AI systems with orchestration, planning, memory, and tool use.
• Experience with document intelligence, OCR, document classification, information extraction, and multimodal AI.
• Experience working with healthcare AI, clinical workflows, medical data, RCM, billing, or claims.
• Familiarity with healthcare standards such as FHIR, HL7, X12/EDI, or similar healthcare data formats.
• Experience with HIPAA, healthcare data privacy, AI security, and responsible AI.
• Experience working with foundation models such as OpenAI, Anthropic, Llama, Mistral, or equivalent.
• Experience optimizing LLM inference cost, latency, scalability, and reliability.

Details

• Location: Hyderabad, India.