Senior Software Engineer & AI Prompt Engineer (GenAI Full Stack)

Pacific Health Group•San Diego, CA

4h•$82,500 - $145,500•Hybrid

About The Position

At Pacific Health Group, we are at the forefront of revolutionizing healthcare, dedicated to improving health outcomes by addressing social determinants of health and coordinating comprehensive community-based services. The Senior Software Engineer & AI Prompt Engineer is responsible for the end-to-end design, development, and optimization of AI-powered software systems across the organization. This role combines full-stack engineering with advanced prompt engineering to build scalable, production-grade Generative AI solutions, including LLM integrations, Retrieval-Augmented Generation (RAG) pipelines, and agentic AI systems. This position owns the full lifecycle of AI applications—from architecture and prompt design to deployment, monitoring, and continuous optimization—ensuring performance, reliability, and measurable operational impact. The role requires both hands-on technical execution and leadership in establishing AI engineering standards, best practices, and system scalability.

Requirements

Bachelor’s degree in Computer Science, Engineering, Data Science, or a related field.
5+ years of experience in software engineering or full-stack development.
Hands-on experience with Generative AI technologies and LLMs (e.g., OpenAI, Anthropic, Gemini).
Strong experience with prompt engineering, RAG pipelines, and agent-based AI systems.
Proficiency in Python and JavaScript/TypeScript.
Experience with modern front-end frameworks (React, Angular, or Vue).
Experience with APIs, microservices architecture, and system integrations.
Familiarity with vector databases and embedding-based systems.
Experience with cloud platforms (AWS, GCP, or Azure).
Strong foundation in data structures, algorithms, and system design.

Nice To Haves

Experience with model fine-tuning, training, and evaluation workflows.
Familiarity with deep learning frameworks such as PyTorch or TensorFlow.
Experience with agent frameworks such as LangChain, LangGraph, or LlamaIndex.
Knowledge of AI governance, risk, and compliance frameworks.
Experience leading engineering teams or delivering client-facing AI solutions.
Cloud or AI/ML certifications (AWS, Azure, or GCP).

Responsibilities

Design, develop, and optimize prompts, chains, and workflows for LLM-based applications.
Build and manage RAG pipelines, including ingestion, preprocessing, chunking, embeddings, indexing, retrieval, and evaluation.
Architect and implement agentic AI systems, including multi-step reasoning, tool usage, orchestration, and multi-agent patterns.
Establish prompt evaluation frameworks, benchmarking processes, and continuous improvement loops for quality, latency, and cost.
Apply fine-tuning and domain adaptation techniques where necessary.
Ensure responsible AI practices, including governance, safety, and reliability in production environments.
Design and build scalable backend systems using Python (FastAPI or similar) and/or Java-based architectures.
Develop modern front-end applications using React, Angular, or Vue frameworks.
Build and maintain APIs, microservices, and integrations across internal and external systems.
Ensure system performance, scalability, observability, and reliability across the stack.
Contribute to architectural decisions and long-term technical roadmap development.
Design and manage data pipelines (ETL) to support AI workflows and model performance.
Implement and maintain vector databases and embedding-based retrieval systems.
Deploy, monitor, and optimize AI models in production environments.
Optimize inference performance, scalability, and cost efficiency.
Leverage cloud platforms (AWS, GCP, Azure) and AI services such as Vertex AI.
Translate business requirements into scalable architectures, technical specifications, and delivery plans.
Lead development efforts, including system design, code reviews, and engineering best practices.
Mentor team members and promote a culture of engineering excellence and AI adoption.
Collaborate cross-functionally with product, operations, and leadership teams to deliver impactful AI solutions.
Evaluate emerging AI tools, frameworks, and technologies for practical implementation.
Develop and implement testing strategies across application and AI layers, including unit, integration, regression, and performance testing.
Maintain CI/CD pipelines and ensure production readiness of all systems.
Monitor system performance, manage incidents, and drive continuous optimization.
Ensure high standards of reliability, scalability, and consistency across releases.
Ensure all AI systems, data pipelines, and integrations comply with HIPAA and organizational data security standards.
Implement safeguards for handling Protected Health Information (PHI), including encryption, access control, and secure transmission.
Establish audit trails, monitoring systems, and governance frameworks for AI usage and data handling.
Conduct risk assessments related to AI systems, data exposure, and model behavior.
Collaborate with compliance and security teams to enforce best practices in data protection and AI governance.