AI Engineer – GenAI Application Development

This is a fully remote position, open to applicants in Texas.

📋 Description

• Design and deploy applications powered by large language models (LLMs), retrieval-augmented generation (RAG) pipelines, and AI agents utilizing Python.

• Develop systems for retrieval-augmented generation, which include chunking, embeddings, vector search, hybrid retrieval, and re-ranking techniques.

• Create AI agents using frameworks such as LangChain, LangGraph, CrewAI, or similar agentic structures while adhering to architectural guidelines.

• Construct and manage RESTful APIs using FastAPI or Flask.

• Transition AI solutions from proof-of-concept phases to production environments by containerizing, deploying, and monitoring these systems.

• Conduct evaluations and testing of LLMs to identify regressions and hallucinations.

• Implement LLMOps/MLOps methodologies, which encompass CI/CD pipelines, prompt/version management, automated testing, and monitoring for latency, cost, and quality.

• Write clean, maintainable, and thoroughly tested code in accordance with solid engineering principles.

• Collaborate with architects, engineers, and product owners to convert designs into functional software.

⛳️ Requirements

• A Bachelor's degree in Computer Science, AI/ML, or a related discipline (or equivalent practical experience).

• Over 5 years of experience in software engineering, including at least 2 years of hands-on work with GenAI/LLM-based applications.

• Proficient in Python programming with a strong foundation in software engineering practices.

• Demonstrated experience in building RAG pipelines, including embeddings, vector databases (such as Pinecone, Weaviate, FAISS, ChromaDB, pgvector), and prompt engineering.

• Familiarity with at least one agentic/orchestration framework (e.g., LangChain, LangGraph, CrewAI, or similar).

• Proven experience in developing and deploying RESTful APIs (FastAPI or Flask).

• Understanding of containerization and deployment processes (Docker; basic Kubernetes knowledge is a plus).

• Working knowledge of at least one cloud platform (Azure, AWS, or GCP) for deploying AI workloads.

• Ability to thrive in fast-paced settings and deliver iterative solutions.

• Preferred experience with LLM evaluation frameworks (such as Ragas, LangSmith, DeepEval, or custom benchmarks).

• Exposure to Kubernetes, CI/CD pipelines, and tools for production monitoring/observability is advantageous.

• Preferred experience with SQL/NL-to-SQL pipelines or structured data integration for AI applications.

• Familiarity with Model Context Protocol (MCP) or the development of tool-calling agents is preferred.

• Previous experience in taking AI features from proof-of-concept to full production ownership is advantageous.

• Strong preference for candidates with healthcare knowledge alongside AI/software engineering skills.

• Hands-on experience with healthcare distribution data, pharmacy/NDC-level data, or healthcare EMR/EHR systems (such as HL7, FHIR, or claims) is a significant plus.

🏝️ Benefits

• Medical, dental, and vision insurance.

• Backup dependent care assistance.

• Support for adoption.

• Coverage for infertility treatments.

• Family building assistance.

• Solutions for behavioral health.

• Paid parental leave.

• Paid caregiver leave.

• Opportunities for training programs.

• Resources for professional development.

• Mentorship initiatives.

• Employee resource groups.

• Opportunities for volunteer activities.