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. You will own complex pieces of an AI platform and work directly with applied scientists, backend engineers, and enterprise clients to ship features that are genuinely relied on in production.

Key Responsibilities

• Design and implement RAG pipelines using LangChain, LlamaIndex, or custom architectures - including chunking strategies, embedding selection, and retrieval quality optimization
• Build and optimize vector database integrations (Pinecone, Weaviate, Chroma, pgvector) for semantic search at production scale
• Develop systematic LLM evaluation frameworks: benchmark suites, LLM-as-judge pipelines, regression testing, and hallucination detection
• Run instruction fine-tuning and parameter-efficient fine-tuning (LoRA, QLoRA) on domain-specific datasets
• Collaborate with backend engineers to integrate LLM capabilities into production APIs with appropriate latency, cost, and reliability constraints
• Track and synthesize relevant LLM research and translate high-value advances into product features
• Write observable, tested, and well-documented code; participate in architecture reviews and production incident response

What We Are Looking For

• 2–5 years of software engineering experience, including at least 1 year working with LLMs in a production or near-production context
• Deep familiarity with at least one LLM orchestration framework: LangChain, LlamaIndex, or equivalent
• Hands-on experience with OpenAI, Anthropic, Google Gemini, or open-source model APIs at meaningful scale
• Understanding of embedding models, vector databases, and semantic similarity in production environments
• Strong Python skills; comfort with async programming, REST API design, and cloud infrastructure (AWS/GCP/Azure)
• MS or BS in Computer Science, AI, or related field; equivalent demonstrable experience welcomed
• Bonus: fine-tuning experience (LoRA/QLoRA), RLHF pipeline exposure, multi-agent system design, or contributions to open-source AI tooling

Location San Francisco Bay Area (Hybrid)

• New York City
• Austin, TX
• Remote strongly considered