Senior AI Engineer

At Orion, we’re building the intelligent infrastructure that powers modern financial advisory. As part of our mission to unify planning, investing, and client engagement, we’re looking for a Senior AI Engineer to rapidly deploy cutting-edge large language models (LLMs) and generative AI into production, powering scalable systems and customer experiences.

This is a hands-on, product-facing role focused on shipping working AI features. You’ll work closely with product managers, designers, and engineers to build systems that directly impact thousands of advisors and millions of investor accounts.

Technical Skills

• Proven experience working with large language models (e.g. OpenAI GPT, Claude, LLaMa)

• Familiarity with embedding models, understanding tokenization, prompt engineering and fine-tuning (e.g., LoRA).

• Practical experience with at least 1 vector database:

  • Pinecone, Weaviate, FAISS

• Strong proficiency with orchestration tools like LangChain, Haystack or LlamaIndex for building RAG systems

• Ability to design and implement retrieval-augmented generation (RAG) systems.

• Experience in data preprocessing, chunking and vectorization pipelines

Responsibilities

• Integrate LLMs and generative AI into advisor facing products and workflows

• Design and build RAG systems using internal and external data sources

• Apply techniques like prompt engineering, fine-tuning (e.g. LoRA), and custom embeddings to optimize domain-specific performance

• Evaluate and productionize open-source and proprietary models (GPT-4, Claude, LLaMA, Mistral, etc.)

• Develop APIs and services to deliver AI- powered features at scale

• Collaborate across product and engineering teams to deliver rapidly and reliably

• Continuously measure AI feature quality: accuracy, latency, and user impact

What We’re Looking For

• 5+ years in software engineering, with 2+ years in applied ML or AI

• Deep understanding of LLMs, embeddings, RAG architecture, and vector search

• Strong grasp of prompt design, fine-tuning strategies, and model evaluation

• Proficiency with tools such as:

  • LangChain, LlamaIndex, Pinecone, Weaviate

  • OpenAI, Hugging Face, FastAPI, Docker

• Strong engineering discipline and communication skills, especially in cross-functional settings

Tech Stack

• AI/LLM: OpenAI, Claude, LLaMA, Mistral, Hugging Face Transformers

• RAG/Embeddings: LangChain, LlamaIndex, Pinecone

• Backend: Javascript, .Net, Java

• Infra: AWS, GitHub Actions, optional Kubernetes

Nice to Haves

• Experience with agent-like systems or intelligent workflows

• Background in NLP, recommendations, or personalization

• Worked in fast-paced startups or product-led teams

Why Join Orion

• Build high-impact AI features that ship fast and reach real users

• Help define how LLMs and AI shape the future of financial advice

• Work in a supportive, fast-moving, remote-first culture

• Access the latest tools and models in applied AI

• Join a company with scale and vision — supporting $3.8T+ in assets and 5M+ accounts across 2,400+ advisory firms

#LI-AP1

#LI-Hybrid