AI Engineer - III

This is a high-impact opportunity to join a fast-scaling AI team where you will own key components of GenAI systems end-to-end. As an AI engineer III, you will work closely with senior leadership and cross-functional teams to design, build, and scale production-grade AI solutions. You'll play a critical role in shaping real-world healthcare AI products, working on RAG systems, LLM deployments, and AI agents, while mentoring junior engineers and contributing to technical decision-making.

The candidate will have responsibilities across the following functions:

AI System Development and Ownership:

• Design, build, and deploy production-grade Gen AI solutions using LLMs, RAG architectures, and AI agent frameworks.
• Own end-to-end development of AI features from problem definition to deployment and monitoring.
• Develop advanced prompt engineering strategies and contribute to fine-tuning and model optimization.
• Work with vector databases and large-scale data pipelines for context-aware applications.

Architecture and System Design:

• Contribute to architecture decisions for scalable, reliable, and cost-efficient AI systems.
• Optimize system performance, latency, and cost for production LLM applications.
• Collaborate with senior engineers on evolving systems from prompt-based workflows to RAG and agent-based architectures.
• Ensure high code quality, maintainability, and adherence to engineering best practices.

Product and Cross-functional Collaboration:

• Partner with Product, Clinical, and Business teams to translate requirements into scalable AI solutions.
• Drive experimentation, A/B testing, and iterative improvements for AI-driven features.
• Ensure seamless integration of AI capabilities into core product workflows.
• Work towards compliance with healthcare standards such as HIPAA and coding systems (ICD-10 CPT).

MLOps and Production Systems:

• Lead deployment, monitoring, and maintenance of Gen AI systems in production.
• Implement observability, logging, and alerting for AI pipelines and services.
• Drive cost optimization initiatives for LLM usage and infrastructure.
• Maintain model lifecycle practices, including versioning, evaluation, and deployment pipelines

Mentorship and Innovation:

• Mentor junior engineers and contribute to team knowledge sharing.
• Stay updated with advancements in Gen AI, LLMs, and AI agents, and apply them to real-world problems.
• Contribute to POCs and innovation initiatives to enhance product capabilities.

The core requirements for the job include the following:

Gen AI and Technical Expertise:

• 3+ years of experience in AI/ML or backend systems, with strong hands-on experience in Gen AI/LLM-based applications.
• Deep understanding of RAG architectures, vector databases, and AI agent frameworks.
• Experience building and scaling production-grade Gen AI systems (deployment, monitoring, cost optimization).
• Strong grasp of prompt engineering, model evaluation, and fine-tuning techniques.
• Solid understanding of MLOps practices and model lifecycle management.

Core Skills:

• Strong programming skills in Python.
• Experience with cloud platforms (AWS/GCP/Azure).
• Good understanding of system design, distributed systems, and scalable backend architecture.
• Strong problem-solving and analytical skills.