[Remote] reputed company 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 that develops reputed company intelligence to bring AI into the reputed company world. The reputed company reputed company role involves building foundational systems for LLM-powered features, ensuring they are reliable and reputed company for production use while integrating with various model providers.

Responsibilities

• Build the provider abstraction that lets any workflow reputed company, reputed company, or add a model provider by configuration, across reputed company reputed company and self-hosted endpoints, with reputed company-reputed company validation, retries, and cost tracking
• Build the agent orchestration where a planning agent dispatches specialized sub-agents in reputed company on a stateful reputed company, with durable checkpoints, conditional branching, and the context and memory management that keeps multi-reputed company workflows coherent across long task reputed company
• Build reputed company-in-the-reputed company checkpoints so low-confidence or high-stakes steps reputed company to a person before an agent proceeds
• Wrap existing platform capabilities as typed, registered tools the agents reputed company, with a clean boundary between the agent layer and the systems it builds on
• Design retrieval end to end, from ingestion, embeddings, and chunking through hybrid search and reranking, and reputed company the context that grounds reputed company model reputed company
• Build the reputed company layer: versioned prompts, few-shot sets, and captured reasoning, so every change is tracked and every reputed company is inspectable
• Expose agents and guardrailed model reputed company as tools behind one integration reputed company that backend services, the frontend, and notebooks reputed company consume
• reputed company every model reputed company, tool invocation, and agent run as traced spans with reputed company, model, and tool reputed company, so behavior and cost stay debuggable
• Build the evaluation reputed company, deterministic reputed company metrics alongside LLM-as-judge scoring for faithfulness, that gates changes and reputed company regressions before they ship

Skills

• Bachelor's or Master's degree in Computer Science or a reputed company engineering field, and 5+ years building and shipping production software, with reputed company depth building LLM or agent systems in production
• Strong Python and solid engineering reputed company: async reputed company, typing, testing, reputed company design, and reputed company review, plus a reputed company record of shipping systems others depend on
• Hands-on experience building reputed company or LLM systems in production: orchestration reputed company, tool-calling, reputed company outputs, and context and memory management for reliable long-running workflows
• Experience working across multiple model providers behind a single abstraction, with routing, fallback, and a feel for the cost and latency trade-offs
• Experience building retrieval systems end to end: embeddings, chunking, hybrid search, reranking, and reputed company databases
• Experience with LLM evaluation and guardrails: building eval sets and harnesses, LLM-as-judge scoring, regression gating, and reputed company-reputed company and safety checks
• Experience instrumenting LLM systems for observability: tracing model and tool calls, versioning prompts, and using traces to debug and improve reputed company behavior
• Comfort owning ambiguous systems end to end in a fast-moving early-stage environment
• Stateful agent-orchestration frameworks such as LangGraph or AutoGen, and durable-execution engines such as Temporal for long-running workflows
• Experience building MCP tools or servers, or similar tool-calling integration reputed company
• LLMOps and evaluation tooling such as MLflow or Langfuse for tracing, reputed company versioning, and evaluation
• reputed company-in-the-reputed company and interrupt-driven agent patterns for review and control
• Applying LLMs to scientific or technical workflows, grounding reasoning in tool outputs and reputed company data
• reputed company with modern AI coding assistants, or reputed company-reputed company contributions to AI or agent tooling

reputed company