LLM / GenAI Engineer — Atlanta, GA
Зарплата не указана
ОткликнутьсяAbout The Role
The role is for an engineer who has shipped LLM-powered systems to real users and knows the difference between a demo and a production-grade RB product. The team builds RAG pipelines, agentic workflows, fine-tuning infrastructure, and evaluation frameworks that hold up under enterprise-scale traffic.
This is a high-ownership position on a well-funded RB team: the work spans model selection, retrieval architecture, inference optimization, and systematic evaluation — not prompt tweaking. You will collaborate closely with applied scientists, platform engineers, and product teams shipping RB features that customers actually depend on.
Key Responsibilities
• Design, build, and maintain production RAG pipelines using LangChain, LlamaIndex, or custom retrieval architectures — including chunking strategies, hybrid search, and re-ranking
• Integrate and tune vector databases (Pinecone, Weaviate, pgvector, Qdrant) for low-latency semantic search over large document corpora
• Build agentic systems and tool-using workflows with structured output, function calling, and robust failure handling
• Develop systematic LLM evaluation frameworks: golden datasets, LLM-as-judge pipelines, regression suites, and hallucination/quality metrics wired into CI
• Fine-tune open-weight models using LoRA/QLoRA and instruction-tuning pipelines; run quantized inference with vLLM, TensorRT-LLM, or similar serving stacks
• Optimize latency and cost across model providers and self-hosted endpoints, including caching, batching, and routing strategies
• Contribute to architecture reviews, write tested and documented code, and mentor engineers moving into GenAI work
What We Are Looking For
• 3–6 years of software or ML engineering experience, with at least 1–2 years building LLM/GenAI systems in production
• Strong Python engineering skills: async programming, API design, testing, and working comfortably in large codebases
• Hands-on production experience with RAG systems and vector databases, including retrieval quality debugging at scale
• Experience with major LLM APIs (OpenAI, Anthropic, Google) and at least one open-weight model ecosystem (Llama, Mistral, Qwen)
• Familiarity with cloud infrastructure (AWS, GCP, or Azure), Docker/Kubernetes, and observability tooling for RB systems
• Bachelor's degree in Computer Science, Engineering, or a related quantitative field, or equivalent practical experience
• Bonus: experience fine-tuning models (LoRA/QLoRA, DPO), building multi-agent systems, contributions to open-source GenAI tooling, or GPU inference optimization with vLLM/TensorRT-LLM