Senior Generative AI Engineer (Google Gemini & Vertex AI) - Remote

About the role

The Senior Generative AI Engineer will lead the design and implementation of Google Gemini and Vertex AI‑based generative AI solutions, building RAG pipelines, high‑performance APIs, vector databases, data extraction pipelines, and domain‑specific model fine‑tuning. The role involves creating backend services, automating requirements generation, documenting solutions, and collaborating with SMEs and test teams while ensuring AI guardrails, MLOps, and cost governance, all on a remote 6‑month W2 contract.

About the company

DivIHN is a CMMI ML3‑certified technology and talent solutions firm founded in 2002 that connects skilled professionals with commercial and public sector organizations. It offers consulting, custom projects, and resource augmentation services focused on IT asset performance, emphasizing standardization, specialization, and collaboration, and promotes an inclusive, purpose‑driven culture.

Requirements

• 4+ years professional software/ML engineering experience with AI/ML focus in the last 1–2 years
• Hands‑on experience with Google Gemini and Vertex AI, including deployment, grounding, containerization (Docker) and deployment via Cloud Run or GKE
• Proficiency in Python and modern ML/AI frameworks (PyTorch, LangChain, LangSmith) for building autonomous LLM agents and RAG pipelines
• Proven experience building AI/LLM agents and tool‑calling systems in Python against unstructured, multi‑source data
• Expertise in RAG pipelines, prompt engineering, context tuning, grounding, and vector databases (Milvus, Postgres/Pgvector) with knowledge of hybrid search, re‑ranking, and semantic caching
• Demonstrated ability to ingest, clean, extract, and structure text, tables, and images from unstructured documents for LLM training and usage
• Full‑stack engineering for AI‑powered services (backend APIs + front‑end integration)
• 2+ years building RAG pipelines & LLM applications on Google Gemini / Vertex AI using Python, LangChain, and LangSmith
• Experience architecting and serving custom REST APIs (preferred)
• Experience in regulated/compliance‑sensitive domains such as healthcare or medical device guidelines (preferred)
• Experience integrating multiple LLM APIs beyond a single provider (preferred)
• Designing and deploying high‑throughput REST APIs (FastAPI/Flask) (preferred)
• Front‑end development/integration experience (Streamlit, Gradio, React/Next.js) (preferred)
• Minimum Bachelor’s degree in Software/Computer/IT/Systems/Biomedical Engineering plus 3 years experience
• Technical evaluation of Python proficiency, RAG architecture concepts, and API/Agent design
• Software skills: Python (AsyncIO, OOP), SQL, PyTorch, LangChain, LangSmith, Vertex AI SDK, FastAPI, Flask, REST, SSE, Milvus, Pgvector, Qdrant, Redis, Streamlit, Gradio, basic React/Next.js, pytest, JUnit, NeMo Guardrails, Docker, GCP (Vertex AI, Cloud Run, GKE), Git
• Professional AI/ML certifications (e.g., Certified AI Professional, Google Cloud ML Engineer) considered a plus