Description

Responsibilities • Design, build, and fine-tune NLP/LLM solutions for business use cases (e.g., classification, summarization, Q&A). • Develop efficient, well-documented Python code for training, inference, and evaluation pipelines. • Build RAG applications using embeddings, vector databases, and prompt engineering techniques. • Integrate LLM applications into services/APIs and ensure performance, reliability, and scalability. • Establish model evaluation, monitoring, and governance practices (quality, safety, bias, drift). • Collaborate with data engineering and platform teams on data pipelines, deployments, and CI/CD. Required Qualifications • 6+ years of overall experience in software development focusing on AI/ML engineering. • 2+ years of hands-on experience with deep learning for NLP/GenAI. • Strong Python proficiency, including writing production-quality, testable, maintainable code. • Experience with deep learning frameworks and libraries: PyTorch or TensorFlow; Hugging Face Transformers. • Solid understanding of deep learning architectures and modern NLP/LLM concepts (tokenization, attention/transformers, fine-tuning approaches). • Experience building rapid prototypes and APIs using FastAPI/Flask and/or Streamlit. Preferred Qualifications • Experience with LLM orchestration frameworks (LangChain, LlamaIndex, Semantic Kernel, or similar). • Experience with vector databases and embedding workflows (e.g., FAISS, Pinecone, Weaviate, Chroma, Azure AI Search). • Experience deploying and scaling ML/LLM workloads on cloud platforms (Azure preferred; GCP/AWS acceptable). • Familiarity with agentic architectures and multi-agent patterns (e.g., AutoGen or similar). • Healthcare domain knowledge and/or experience building solutions in regulated environments. Standard Technical Skills • MLOps & Deployment: Model packaging and serving, CI/CD, containers (Docker), orchestration (Kubernetes), experiment tracking (MLflow), model registry, monitoring/observability. • LLM Evaluation: Offline/online evaluation, prompt/version management, automated testing, hallucination and factuality checks, retrieval evaluation, human-in-the-loop review. • Software Engineering: Git, code reviews, unit/integration testing (pytest), REST APIs, basic system design, performance optimization. • Security & Compliance: Secure coding, secrets management, PII/PHI handling, access control; familiarity with responsible AI principles is a plus

Key Skills

Education

Bachelor's degree