Software Engineer - AI Engineer II/III

Applied Medical is a new generation medical device company with a proven business model and commitment to innovation fueled by rapid business growth and expansion. Our company has been developing and manufacturing advanced surgical technologies for over 35 years and has earned a strong reputation for excellence in the healthcare field. Our unique business model, combined with our dedication to delivering the highest quality products, enables team members to contribute in a larger capacity than is possible in typical positions.

We are seeking a highly skilled AI Engineer with deep expertise in Large Language Models (LLMs), AI agent frameworks, and Model Context Protocols (MCP). The ideal candidate will design, develop, and deploy advanced AI-powered solutions that leverage LLMs for reasoning, planning, and autonomous decision-making. In this role, you will build agentic systems capable of performing multi-step tasks, interacting with external systems, integrating with APIs and tools, and orchestrating complex workflows end-to-end. You will also implement and optimize MCP-based architectures to ensure reliable tool usage, persistent context management, and robust coordination between agents and backend services.

Collaboration is a fundamental part of our organization's culture and is essential to our continued success. As such, the successful candidate for this position is expected to work on-site, enabling them to engage fully with colleagues and contribute to cross-functional initiatives. Therefore, the ability to work collaboratively and contribute to a positive and supportive team environment is a key requirement for this role.

Key Responsibilities:

• Design, fine-tune, and deploy LLM-based applications for various use cases (retrieval, reasoning, planning, automation).
• Develop AI agents that integrate with external tools, APIs, and databases using frameworks like LangChain, LangGraph, AutoGen or custom solutions.
• Implement and optimize RAG pipelines, vector databases, and prompt-engineering strategies for context-aware responses.
• Build scalable backend systems to support LLM-based solutions in production environments.
• Leverage and implement Model Context Protocols to enable seamless context sharing and coordination between LLMs, agent frameworks, and external resources.
• Research and evaluate emerging LLM and agentic technologies to drive innovation.
• Collaborate with cross-functional teams (data science, product, engineering) to align AI solutions with business goals.
• Ensure responsible AI practices, model safety, and compliance with data privacy regulations.

• • Bachelor’s or Master’s degree in Computer Science, AI/ML, or related field (Ph.D. a plus).
  • 2+ years of experience building and deploying AI applications using LLMs (OpenAI, Anthropic, Hugging Face, etc.).
  • Strong experience with Python, Git, FastAPI/Flask, and common ML frameworks (PyTorch, TensorFlow).
  • Hands-on experience with agent frameworks (AutoGen, LangGraph, CrewAI, etc.) and orchestration strategies.
  • Proficiency in vector databases (Pinecone, ChromaDB, FAISS) and embedding techniques.
  • Solid understanding of prompt engineering, RAG, and LLM optimization.
  • Familiarity with on-prem deployment and cloud environments (Azure, AWS, GCP) and containerization (Docker, Kubernetes).
  • Experience implementing Model Context Protocols for enhanced context management and interoperability across agentic systems.
  • Excellent problem-solving skills and ability to work in a fast-paced environment.

• Competitive compensation range: $80000 - $140000 / year (California).
• Comprehensive benefits package.
• Training and mentorship opportunities.
• On-campus wellness activities.
• Education reimbursement program.
• 401(k) program with discretionary employer match.
• Generous vacation accrual and paid holiday schedule.