Backend AI Engineer

Posted 1mo ago

The employer’s full description could not be read from their board. This is a summary of the posting — follow the apply link for the original.

Craft and refine effective prompts for RAG, grounding, and context tuning
Develop asynchronous microservices (FastAPI) using SSE or WebSockets to stream real-time LLM responses
Design, develop, and implement robust Vector Databases using LLMs and modern retrieval technologies
Build and optimize pipelines to extract and structure multi-modal data from unstructured documents
Fine-tune and train generative AI models using client engineering data and domain knowledge
Design and implement scalable backend APIs (FastAPI/REST) and UI integration interfaces
Develop backend functionalities to automatically generate technical requirements from design documents
Thoroughly document architecture, code, REST endpoints, and model training procedures
Partner closely with Subject Matter Experts, System Engineers, and V&V Test teams to optimize AI-powered workflows
Implement hallucination checks, PII masking, and guardrails for medical device context

4+ years of professional software/ML engineering experience with dedicated AI/ML focus in last 1-2 years
Hands-on experience with Google Gemini model family and Vertex AI
Experience with containerization (Docker) and deploying services via Cloud Run or GKE (Kubernetes)
Proficiency in Python and modern ML/AI frameworks (PyTorch, LangChain, LangSmith)
Proven experience building AI/LLM agents and tool-calling systems in Python
Expertise in RAG pipelines, prompt engineering, context tuning, grounding, and Vector Databases (e.g., Milvus, Postgres/Pgvector)
Understanding of advanced RAG architecture including Hybrid Search, Re-ranking models, and semantic caching
Demonstrated ability to ingest, clean, extract, and structure text, tables, and images from unstructured documents
Experience with FastAPI for high-performance API engineering
Experience with Server-Sent Events (SSE) or WebSockets for streaming real-time LLM responses

Direct experience designing and deploying high-throughput REST APIs (e.g., FastAPI/Flask)
Familiarity with medical device development regulations and compliance (e.g., FDA guidelines, ISO 13485)
Experience integrating multiple LLM APIs beyond a single vendor (e.g., OpenAI, AWS Bedrock, Anthropic Claude)
Front-end development/integration experience for UI design (e.g., Streamlit, Gradio, React/Next.js integration)

Skills