LLM / GenAI Engineer

About The Role

The role is for someone who has moved beyond basic prompting and understands what it takes to build production-grade AI systems: robust RAG pipelines, agentic workflows, fine-tuning pipelines, and systematic evaluation frameworks. The engineering team owns complex pieces of a rapidly scaling AI platform, working directly with applied researchers, backend engineers, and product stakeholders to deliver high-impact generative AI solutions.

Key Responsibilities

• Design and implement end-to-end RAG pipelines using LangChain, LlamaIndex, or custom Python orchestration frameworks
• Build and optimize vector database integrations including Pinecone, Weaviate, and pgvector for semantic search at production scale
• Develop systematic LLM evaluation frameworks using benchmark suites, LLM-as-judge pipelines, and rigorous regression testing
• Run parameter-efficient fine-tuning workflows like LoRA and QLoRA on domain-specific datasets using PyTorch and Hugging Face
• Maintain deployed LLM applications for latency, hallucination rates, cost, and output quality using modern observability tooling
• Write observable, tested, and well-documented code while actively participating in architecture reviews and team engineering standards

What We Are Looking For

• 3-6 years of software engineering experience, with a minimum of 2 years specifically focused on building production LLM and Generative AI systems
• Deep familiarity with LLM orchestration frameworks, prompt engineering best practices, and context window management
• Demonstrated experience with embedding models, vector databases, and semantic similarity search in high-throughput environments
• Strong Python development skills including async programming, REST API design, and containerization with Docker
• Solid understanding of ML fundamentals, transformer architectures, and cloud infrastructure on AWS, GCP, or Azure
• Bonus: Open-source contributions to GenAI tooling, published research, or hands-on experience with multi-agent frameworks like AutoGen or CrewAI