AI Engineer (Applied LLMs)

What you will do

• Research, prototype, and productionize LLM-powered agents for gap analysis, policy drafting, and evidence evaluation
• Fine-tune open-source or proprietary models with retrieval-augmented generation, context engineering, and agent orchestration
• Build evaluation harnesses that measure factual accuracy, explainability, and latency in real customer scenarios
• Work side-by-side with backend engineers to expose AI capabilities via APIs, Slack bots, and browser extensions
• Keep the team current on advances in model architectures, vector stores, and inference optimization

You should have

• Solid software engineering fundamentals (Python preferred; Java/Go/TypeScript ok)
• 2 + years crafting ML/AI solutions or an outstanding portfolio of AI side projects
• Demonstrated skill using frameworks such as PyTorch, TensorFlow, Hugging Face, LangChain, LlamaIndex, or vLLM
• Experience deploying models behind scalable, secure endpoints in the cloud
• Familiarity with RAG pipelines, embeddings, and vector databases (Weaviate, Pinecone, PGVector, etc.)
• The creativity to turn ambiguous audit workflows into deterministic agent loops

Nice-to-haves

• Contributions to open-source AI projects
• Knowledge of compliance standards (SOC 2, ISO 27001, HIPAA)
• Experience with GPU orchestration and cost optimization