• Data Pipeline & Knowledge Base Construction:  

• Design, implement, and optimize robust pipelines for ingesting, parsing, and extracting structured information from complex documents (leveraging OCR, document layout analysis, Named Entity Recognition (NER), and Relationship Extraction (RE)). 

• Develop rich, nested JSON schemas for representing structured data and ensure scalable storage 

• Generate and manage high-quality vector embeddings for efficient retrieval-augmented generation (RAG) within a Vector Database. 

• Language Model (LM) Development & Fine-tuning:  

• Research, select, and experiment with appropriate open-source Language Models (Large & Small) (e.g., Phi-3, Mistral, Llama, Nemotron-H families) for specialized tasks. 

• Design and execute efficient fine-tuning strategies (e.g., LoRA, QLoRA, full fine-tuning) on curated, domain-specific datasets to achieve precise performance for tasks like coverage determination, code lookups, and policy rule application. 

• Explore and implement knowledge distillation techniques to transfer capabilities from larger models to smaller, more efficient LMs. 

• Agentic System Design & Implementation:  

• Build and maintain the core agentic framework, including the orchestrator that intelligently routes queries and coordinates interactions between various specialized LM tools. 

• Develop and integrate "tools" (specialized LMs and external APIs) that perform atomic medical necessity tasks, ensuring strict behavioral alignment and structured outputs. 

• MLOps & Deployment:  

• Deploy, manage, and monitor LMs and agentic components on Google Cloud Platform (GCP) using services like Vertex AI, GKE, Cloud Functions, and Cloud Run. 

• Implement robust MLOps practices for continuous integration, continuous delivery (CI/CD), model versioning, and performance monitoring (latency, throughput, accuracy). 

• Continuous Improvement & Research:  

• Establish effective feedback loops from end-user interactions and system logs to identify areas for model improvement. 

• Curate and expand training datasets, ensuring data privacy (PHI/PII masking) and legal compliance. 

• Stay abreast of the latest research in LMs, agentic AI, NLP, and document understanding, applying relevant advancements to our system. 

• Collaboration:  

• Work closely with subject matter experts, product managers, and other engineers to translate complex requirements into technical solutions and evaluate system performance. 

• Bachelor's or Master's degree in Computer Science, Machine Learning, Artificial Intelligence, or a related quantitative field. 

• 3+ years of professional experience in Machine Learning Engineering, with a strong focus on NLP. 

• Proven experience with Language Models (LMs), including model selection, fine-tuning, and deployment. 

• Strong proficiency in Python and familiarity with ML frameworks (e.g., PyTorch, TensorFlow, Hugging Face Transformers). 

• Solid understanding and hands-on experience with core NLP techniques and architectures, especially Transformers. 

• Experience with cloud platforms, particularly Google Cloud Platform (GCP), including services like Vertex AI, Cloud Storage, and compute services. 

• Familiarity with MLOps principles and tools for model serving, monitoring, and pipeline automation. 

• Excellent problem-solving skills, attention to detail, and ability to work independently and collaboratively. 

• Active use of artificial intelligence (AI) tools and techniques to enhance performance, drive innovation, and improve decision-making across business functions. 

• Ability to leverage AI tools and platforms to streamline workflows, improve decision-making, and drive innovation. 

• Curiosity and adaptability in exploring emerging AI technologies, with a mindset for continuous learning and experimentation. 

What Will Make You Stand Out (Preferred Qualifications): 

• Hands-on experience building or contributing to agentic AI systems or multi-agent frameworks. 

• Direct experience with document processing technologies such as OCR, layout parsing, Document AI, or custom information extraction from unstructured text. 

• Experience with Vector Databases (e.g., pgvector, Pinecone, Weaviate, Qdrant) and RAG architectures. 

• Exposure to the healthcare domain, particularly understanding medical terminology, CPT/ICD codes, or regulatory documents.