LLM Engineer (Visa Sponsorship)

Spherecast
New York
Workplace: OnsiteFull timeFunction: Product ManagementSkills: ["System design","Iteration","Prompting","Observability","Building end-to-end"]

Build Agnes, Spherecast’s AI Supply Chain Manager, end-to-end—from prototypes to production—by designing LLM-powered workflows that decide what to produce, where to manufacture, and how to move goods through real-world systems. You’ll work with modern LLM APIs and HuggingFace, create evaluation and monitoring pipelines, and ship robust multi-step agent flows that perform reliably on messy, operational data to drive real outcomes.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Spherecast
Spherecast
4 days ago

LLM Engineer (Visa Sponsorship)

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 9 hours agoStatus: Live

Job Summary

Build Agnes, Spherecast’s AI Supply Chain Manager, end-to-end—from prototypes to production—by designing LLM-powered workflows that decide what to produce, where to manufacture, and how to move goods through real-world systems. You’ll work with modern LLM APIs and HuggingFace, create evaluation and monitoring pipelines, and ship robust multi-step agent flows that perform reliably on messy, operational data to drive real outcomes.
Location: New York
Workplace: Onsite
Employment Type: Full time
Job Function: Product Management

Key Responsibilities

  • •Own Agnes from prototypes to production, turning prompts and agent flows into tested, evaluated pipelines.
  • •Design and implement LLM integrations using modern LLM APIs and HuggingFace.
  • •Build robust multi-step agent flows with tool/function design and structured outputs that handle edge cases.
  • •Create and maintain evaluation pipelines to iterate quickly and safely on workflows and prompts.
  • •Implement LLM observability and monitoring (logging, traces, quality metrics, feedback loops) to improve production accuracy over time.

Pay and Benefits

Perks:Visa Sponsorship

Key Requirements

  • •Hands-on experience shipping with modern LLM APIs (e.g., Anthropic, OpenAI, DeepSeek, OpenRouter, Gemini, Moonshot).
  • •Strong intuition for LLM selection, including latency/cost tradeoffs and appropriate use cases.
  • •Practical experience using the HuggingFace ecosystem in real projects.
  • •Experience building production-grade LLM automations or agents (not just demos).
  • •Ability to design and maintain evaluation pipelines, plus strong prompting and system-design skills for robust multi-step agent flows.
Experience:AISupply chain
Skills:System designIterationPromptingObservabilityBuilding end-to-end
Tech Stack:LLM APIsAnthropicOpenAIDeepSeekOpenRouterGeminiMoonshotHuggingFaceAgentsStructured outputsLoggingTraces

Company Brief

Spherecast
Builds an AI-driven platform for creating and deploying realistic virtual humans and live avatars for streaming, broadcasts, and virtual events, enabling real-time presenter substitution and interactive on-screen hosts using machine learning and computer vision.
Industry: Digital Media
Company Size: Small (11 to 50 employees)
Growth: Early Stage Startup
Website