AI Engineer

Role Overview We’re looking for an AI Engineer who wakes up in the morning thinking about agents, workflows, embeddings, vector stores, LLM orchestration, and how to make machines do more so humans can do less busywork and more winning. This engineer will architect, build, and optimize the next generation of agentic AI systems powering our conversational AI, automation frameworks, document intelligence, and end-to-end workflow orchestration. If “Autonomous Agents,” “LLM Tool Use,” and “Multi-Step Reasoning” don’t just sound familiar but actually get you a little excited… you’re our person. You’ll collaborate with product, engineering, and leadership teams to turn complex mortgage and operational tasks into clean, scalable AI logic that just works. Encouragement note: If you like building tech that feels like magic to users, you’ll love it here. Key ResponsibilitiesAgentic AI Development - Build and deploy LLM-powered autonomous agents capable of taking actions, making decisions, and orchestrating complex workflows across our systems. - Architect multi-agent systems that communicate, coordinate, and self-evaluate to improve reliability and performance. - Implement memory, reasoning, and planning modules that make agents function like high-performing team members… minus the coffee breaks. Workflow Automation - Convert business processes into event-driven automation pipelines powered by LLMs and traditional software. - Integrate agents with internal and external tools (APIs, databases, RPA, task queues, knowledge bases). - Build robust monitoring, safety checks, and fallback logic for mission-critical automations. Conversational & Generative AI - Develop production-grade chat interfaces with retrieval augmentation, long-context reasoning, tool calling, and user-level personalization. - Optimize prompts, system instructions, and chain-of-thought structures for stability and high accuracy. - Create generative components for messaging, documentation, analysis, and dynamic UI content. Framework & Model Expertise - Work hands-on with industry-leading frameworks including (but not limited to): - LangChain, LlamaIndex, CrewAI, AutoGen, OpenAI Assistants, Hugging Face, Haystack - Vector DBs such as Pinecone, Weaviate, Chroma, Milvus - LLM orchestration tools like Ray, Modal, Databricks, AWS Bedrock - Evaluate, fine-tune, and deploy cutting-edge open-source and proprietary LLMs. QualificationsRequired - 3–7 years in Machine Learning, AI Engineering, or Applied NLP. - Proven experience building agentic AI workflows or autonomous LLM-driven systems. - Strong knowledge of Python, fast API frameworks, concurrency, and cloud-native architecture (AWS preferred). - Deep understanding of LLM behavior, prompting, embeddings, RAG, vector search, and tool calling. - Experience deploying production-grade generative AI solutions (chatbots, automation pipelines, document understanding modules). - Familiarity with model fine-tuning, dataset curation, and evaluation frameworks. - Ability to translate requirements into technical architectures with clear plans and execution roadmaps. Bonus Superpowers - Experience in financial services, mortgage workflows, document parsing, or identity verification systems. - Contributions to open-source AI/ML frameworks. - Understanding of how to build reliability, guardrails, and observability for LLM agents. - Ability to juggle multiple frameworks without breaking a sweat (or the build). - A bias toward speed and iteration — you like to ship fast and learn fast. -