Work All Remote

The Role:

We are looking for a Senior AI Engineer to lead the development and scaling of our LLM-powered solutions. While your foundation is in Python, this role is specifically designed for an expert who understands the nuances of the generative AI lifecycle—from prompt engineering and RAG architecture to fine-tuning and production-grade deployment. You will be responsible for transforming raw model capabilities into robust, reliable, and scalable backend services.

What we are looking for:

• Expert-level Python skills with a deep understanding of asynchronous programming and backend architecture.
• Proven experience building and deploying production-level applications using Large Language Models (LLMs).
• Strong experience with SQL and NoSQL databases, specifically optimized for high-dimensional vector search.
• Familiarity with deploying AI models in cloud environments (AWS, GCP, or Azure) and managing CI/CD for AI services.
• A “first-principles” approach to solving the unique challenges of non-deterministic AI outputs
• Experience with fine-tuning open-source models using techniques like LoRA or QLoRA.
• Knowledge of agentic frameworks and autonomous AI agents.
• A background in traditional NLP (Spacy, NLTK) or classic Machine Learning.

Responsibilities:

• Architect and implement complex AI workflows using frameworks like LangChain, LlamaIndex, or Haystack.
• Design and optimize Retrieval-Augmented Generation (RAG) pipelines, including vector database management (Pinecone, Weaviate, or Milvus) and advanced indexing strategies.
• Evaluate and implement strategies for model selection (OpenAI, Anthropic, or Open Source like Llama 3) based on latency, cost, and performance requirements.
• Develop high-performance Python backends (FastAPI or Flask) to serve AI features to our global user base.
• Build robust evaluation frameworks to measure LLM accuracy, reduce hallucinations, and monitor production performance using tools like LangSmith or Arize Phoenix.
• Work closely with product and engineering teams to identify high-impact AI opportunities and navigate the technical trade-offs of generative AI.