Ai Engineer 3

## About the role As an AI Engineer III, you will be a senior individual contributor responsible for designing, building, and optimizing production-grade Gen AI systems. You will work on LLMs, RAG pipelines, and AI agents, owning critical components end-to-end—from experimentation to deployment. This role is ideal for someone who combines deep technical expertise with strong product intuition, and thrives in a fast-paced startup environment. ## Responsibilities ### Gen AI System Development - Design and implement RAG pipelines, LLM-based workflows, and AI agents - Build scalable systems for medical coding automation and clinical NLP - Develop prompt strategies, evaluation pipelines, and fine-tuning workflows - Work with structured + unstructured healthcare data (EHRs, notes, codes) ### Architecture & Technical Ownership - Own end-to-end architecture of Gen AI features from prototype → production - Make decisions on model selection, embeddings, vector databases, and orchestration frameworks - Optimize systems for latency, accuracy, and cost efficiency - Contribute to architecture discussions for evolving AI platform capabilities ### Production & MLOps - Deploy and maintain Gen AI systems in production environments - Implement monitoring, observability, and evaluation frameworks - Build pipelines for model versioning, experimentation, and A/B testing - Ensure system reliability, scalability, and fault tolerance ### Cross-functional Collaboration - Partner with Product, Clinical, and Data teams to translate requirements into solutions - Work closely with engineering teams to integrate AI into production workflows - Contribute to defining product requirements and success metrics ### Innovation & Research - Stay up-to-date with latest advancements in LLMs, RAG, and AI agents - Prototype new approaches and evaluate emerging tools/frameworks - Translate research into practical, production-ready systems ## Requirements ### Core Technical Skills - 4–7 years of experience in AI/ML, NLP, or Deep Learning - Strong hands-on experience with: - Large Language Models (OpenAI, open-source LLMs, etc.) - RAG architectures and vector databases - Prompt engineering and model evaluation - Proficiency in Python and ML frameworks (PyTorch, TensorFlow) ### Gen AI Production Experience - Experience building and deploying production-grade Gen AI systems - Understanding of: - Model lifecycle (training, evaluation, deployment) - LLM cost optimization strategies - Observability and monitoring for AI systems ### Systems & Engineering - Experience with cloud platforms (AWS/GCP/Azure) - Knowledge of microservices, APIs, and distributed systems - Familiarity with data pipelines and real-time processing systems - Strong software engineering fundamentals (testing, CI/CD, code quality) ### Healthcare (Preferred) - Exposure to healthcare data or workflows - Familiarity with: - HIPAA or regulated environments - Medical coding systems (ICD-10, CPT, SNOMED) ## What Sets You Apart - Experience building AI agents or multi-step reasoning systems - Hands-on work with evaluation frameworks for LLM accuracy - Ability to balance research exploration with production delivery - Strong ownership mindset and ability to drive projects independently ## What we offer - Competitive compensation with equity upside - Hybrid work setup with flexibility - Opportunity to work on cutting-edge Gen AI in healthcare - High-impact role influencing real-world clinical and financial outcomes - Learning budget for conferences, certifications, and tools ## Success in this role looks like - Delivering high-accuracy, production-ready Gen AI features - Improving system performance across accuracy, latency, and cost - Driving innovation while maintaining reliability and scalability - Acting as a technical anchor for complex AI problems