LLM / GenAI Engineer

About The Role

The role is for someone who has moved beyond prompting and understands what it takes to build production-grade AI systems: RAG pipelines, agentic workflows, fine-tuning pipelines, and systematic evaluation frameworks.

The team owns complex pieces of an AI platform and works directly with applied scientists, backend engineers, and enterprise clients to deploy high-throughput generative models.

Key Responsibilities

• Design and implement production-grade RAG pipelines using LangChain, LlamaIndex, or custom distributed architectures
• Build and optimize vector database integrations including Pinecone, Weaviate, and pgvector for semantic search at scale
• Develop systematic LLM evaluation frameworks incorporating benchmark suites and automated LLM-as-judge pipelines
• Run instruction fine-tuning and parameter-efficient fine-tuning operations like LoRA and QLoRA on domain-specific datasets
• Optimize model inference latency, throughput, and memory consumption using quantization techniques and vLLM or Triton
• Write observable, tested, and well-documented Python code; participate in rigorous architecture reviews

What We Are Looking For

• 3-6 years of software engineering experience, including at least 2 years working specifically with LLMs and generative AI in production environments
• Deep familiarity with major LLM orchestration frameworks and vector database technologies
• Solid understanding of embedding models, prompt engineering, context window management, and semantic similarity search
• Strong Python skills with comfort in async programming, REST API design, and cloud infrastructure on AWS or GCP
• Bachelor's degree in Computer Science, Artificial Intelligence, or equivalent practical experience
• Bonus: Published research in NLP/AI, contributions to major open-source AI projects, or experience fine-tuning open-source models like Llama and Mistral