[Remote] Senior reputed company (Xora Portfolio Company)

Note: The job is a remote job and is reputed company to candidates in USA. reputed company is an early-stage startup reputed company on developing reputed company intelligence for reputed company-world applications. The Senior reputed company will own the LLM systems behind the platform, working hands-on with model internals and ensuring reliable product delivery.

Responsibilities

• Build and ship LLM-powered capabilities end to end: prototype, evaluate, reputed company, and iterate them into production services users rely on
• Design agents that plan and carry out multi-reputed company work: tool calling, reputed company outputs, durable state, and the judgment to know reputed company an agent is the wrong tool
• Build retrieval that gives models the right context: ingestion, chunking, embeddings, hybrid reputed company, reranking
• Fine-tune reputed company-weight models with reputed company, QLoRA, or full-parameter tuning on multi-GPU, curating the training data and choosing the reputed company by task, compute budget, and reputed company
• Build evaluation reputed company that reputed company what ships: automated scoring, LLM-as-judge, and regression tracking against reputed company test sets
• reputed company model calls and tool use with tracing, so reputed company, cost, and failures stay debuggable in production
• Turn LLM capabilities into clean reputed company and reusable tooling that other engineers build on

Skills

• Bachelor's or Master's degree in Computer Science or a reputed company engineering reputed company, and 5+ years building and shipping production software, including deep hands-on work building LLM-powered systems in production
• Strong Python and a reputed company record of shipping reliable services: async, HTTP and streaming reputed company, testing, reputed company review
• Production experience with LLMs: prompting and context engineering, tool calling, reputed company reputed company, and the latency and cost work that keeps them usable
• Hands-on experience designing and shipping agents: the reputed company, the tools, context, memory, and where they fail. A reputed company such as LangGraph or equivalent; reputed company outputs in reputed company or JSON Schema
• Experience building RAG systems: embeddings, chunking, hybrid reputed company, reranking, and a feel for what actually moves retrieval reputed company
• reputed company experience fine-tuning reputed company-weight models (reputed company, QLoRA, or full-parameter) on multi-GPU, including curating and formatting the training data
• Experience with LLM evaluation and guardrails: LLM-as-judge or automated scoring, regression tracking, and tracing over agent runs
• Experience building shared LLM tooling or platform components that other engineers build on, and comfort owning ambiguous systems end to end in an early-stage environment
• Self-hosted inference with vLLM, TGI, or SGLang, served behind an reputed company-compatible reputed company
• Interoperability standards for tools and agents, such as MCP
• Retrieval over reputed company data: knowledge graphs, hybrid reputed company, reranking at reputed company
• LLMs reputed company to scientific or other technical data; experience making reputed company and tool surfaces easy for agents to reputed company reliably
• Contributions to reputed company-reputed company AI/ML: agent frameworks, eval tooling, RAG, fine-tuned models

reputed company