Senior Full-Stack AI Engineer: Robert Half (recruiting for a client)

This role is for a highly skilled and innovative Senior Full-Stack AI / LLM Engineer to lead the development of cutting-edge AI solutions. You will be responsible for building intelligent systems using large language models (LLMs), generative image models, and multimodal AI technologies. The role involves working across the full stack, from model integration and orchestration to deployment and automation, to deliver scalable, production-grade AI applications.

Responsibilities
Design, develop, and deploy Python-based microservices and APIs for AI-powered applications.

Integrate and fine-tune LLMs from providers such as OpenAI, Anthropic, Meta, and Mistral.

Build Retrieval-Augmented Generation (RAG) pipelines using frameworks like LangChain or LlamaIndex.

Implement semantic search and vector database solutions (e.g., Pinecone, Weaviate, Chroma).

Develop and integrate Text-to-Speech (TTS) and Speech-to-Text (STT) systems using tools like OpenAI Whisper and ElevenLabs.

Work with generative image models including Stable Diffusion and ComfyUI.

Automate workflows using platforms such as n8n, Make, or Zapier.

Deploy AI services on cloud platforms (GCP, AWS, or Azure).

Apply prompt engineering best practices to optimize model performance.

Requirements
Required Qualifications:

Strong proficiency in Python and experience building APIs, microservices, and automation scripts.

Hands-on experience with LLMs and generative AI tools from major providers.

Deep understanding of RAG architectures and experience implementing them in production.

Familiarity with LangChain, LlamaIndex, or similar frameworks.

Experience with vector databases and semantic search techniques.

Knowledge of TTS/STT systems and generative image models.

Proficiency in automation platforms like n8n, Make, or Zapier.

Cloud deployment experience on GCP, AWS, or Azure.

Preferred Qualifications:

Experience with fine-tuning or customizing LLMs.

Familiarity with containerization (Docker) and orchestration (Kubernetes).

A background in machine learning, NLP, or computer vision.

Contributions to open-source AI projects.