AI Engineer

We are hiring an AI Engineer to design, build, and maintain production Retrieval-Augmented Generation systems, agentic AI workflows, and internal-facing AI applications. This person will use Python, AWS services such as Amazon Bedrock, and Databricks Vector Search or comparable tooling to consume governed data and create practical AI capabilities. The role will build multi-step agents using LangGraph, LangChain, CrewAI, or equivalent frameworks; implement tool-use and function-calling with clear human-approval guardrails; and develop front ends using React, Streamlit, Gradio, or similar technologies. Responsibilities also include building REST API integrations and document-processing pipelines that ingest, chunk, embed, and retrieve governed content, including documents stored in SharePoint through Microsoft Graph. The engineer will implement vector embeddings, semantic and hybrid retrieval, and model-evaluation practices addressing drift, hallucination, and overall output quality. The work is highly hands-on and focused on delivering demonstrable solutions, while continuing to learn as the team's AI capabilities mature.

Must-Haves

• 3+ yrs. of data and/or AI engineering experience. Candidates closer to two years may be considered if their hands-on project depth is strong.
• At least one year of hands-on LLM and RAG implementation experience, with at least one production deployment or significant RAG/agentic AI project that can be explained and demonstrated.
• Hands-on experience building agentic AI workflows involving multi-step orchestration, tool use, function calling, and appropriate human-in-the-loop controls.
• Strong Python development experience and a modern software-development foundation; this is not a fit for a traditional developer without meaningful AI implementation experience.
• Experience building at least one user-facing application or internal tool using React, Streamlit, Gradio, or an equivalent framework.
• Application-level REST API development and integration experience connecting AI back ends to applications and tools.
• Working knowledge of AWS cloud services used to build or deploy AI applications.
• Experience with vector embeddings, vector databases or vector search, semantic retrieval, and/or hybrid retrieval patterns.
• Working knowledge of MLOps and model evaluation, including evaluation for drift, hallucination, output quality, and production readiness.
• Strong logical problem-solving ability, curiosity, and a learner-doer mindset suited to a rapidly evolving AI environment.

Nice-to-Haves

• Databricks experience, particularly Databricks Vector Search.
• Amazon Bedrock or comparable managed, multi-model AI service experience.
• Hands-on experience with LangGraph, LangChain, CrewAI, or an equivalent agent framework.
• SharePoint and Microsoft Graph API integration experience for governed document ingestion.
• Experience working in a Microsoft-oriented environment, including Copilot-related solutions.
• Applied machine-learning experience beyond basic generative AI, including model delivery, fine-tuning, or evaluation where applicable.
• SQL, exploratory data analysis, and familiarity with governed healthcare, quality-measure, claims, or regulated datasets.
• Experience presenting or demonstrating completed technical work to internal users or leadership.

TechHuman is an Equal Opportunity Employer and is committed to fostering an inclusive workplace. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex (including pregnancy, sexual orientation, gender identity, or gender expression), age, national origin, citizenship status, disability, genetic information, marital status, military status, protected veteran status, or any other status protected under applicable federal, state, or local law.