LLM / GenAI Engineer

About the role

The LLM / GenAI Engineer will design, build, and operate production AI systems spanning retrieval-augmented generation, tool-using agents, model adaptation, and automated evaluation. The role focuses on turning foundation models into reliable products with measurable gains in quality, latency, cost, and user experience. Working alongside applied scientists, platform engineers, and product teams, this role will own critical components of the GenAI stack—from data and prompt pipelines to inference services, observability, and continuous improvement. The position is remote and aligned with the Atlanta, GA engineering organization.

Responsibilities

• Design and implement production RAG systems using Python, LangChain, LlamaIndex, or custom orchestration frameworks
• Build ingestion, chunking, embedding, retrieval, reranking, and grounding pipelines using vector stores such as Pinecone, Weaviate, Elasticsearch, or pgvector
• Develop agentic workflows with tool calling, structured outputs, memory, human-in-the-loop controls, and robust failure handling
• Create LLM evaluation frameworks covering offline benchmarks, LLM-as-judge workflows, golden datasets, hallucination detection, and regression testing
• Fine-tune and adapt open-source models using supervised fine-tuning, LoRA, QLoRA, prompt optimization, or preference-based methods where appropriate
• Deploy and optimize inference services on AWS, GCP, or Azure using Docker, Kubernetes, and APIs such as vLLM or Hugging Face TGI
• Instrument production systems for latency, token usage, quality, safety, and cost; establish monitoring, alerting, rollback, and incident response practices

Requirements

• 3–8 years of software engineering, machine learning engineering, or applied research experience, including at least 1 year delivering LLM or GenAI systems to production
• Bachelor’s or master’s degree in computer science, machine learning, data science, electrical engineering, or a related technical field

Skills

• Strong Python skills with experience building maintainable services, asynchronous workflows, REST APIs, and automated tests
• Hands-on expertise with LLM application patterns including RAG, embeddings, vector search, prompt engineering, function calling, and structured generation
• Experience with PyTorch, Hugging Face Transformers, model fine-tuning, and inference optimization for open-source or hosted foundation models
• Proficiency with cloud and production infrastructure, including AWS, GCP, or Azure; Docker, Kubernetes, CI/CD, and observability platforms
• Bonus: Experience with Ray, vLLM, Triton, distributed training, multimodal models, privacy and safety controls, or enterprise-scale AI platform development