Founding AI Engineer

Skiffra•Los Angeles, CA
•$220,000 - $250,000•Hybrid

About The Position

Skiffra is building AI-native orchestration systems for operational decision-making in physical industries, beginning with mining and natural resources. The Founding AI Engineer will architect Skiffra’s core intelligence and move agentic workflows from prototypes to production-grade systems that handle enterprise data at scale. This founding-level builder will work across prompt engineering, backend systems, and model optimization, balancing real-world impact with a focus on shipping reliable software. The role involves designing agentic orchestration frameworks, building retrieval-augmented generation pipelines, evaluating model reliability and performance, and selecting pragmatic combinations of frontier models, fine-tuned open-weight models, and deterministic heuristics. The engineer will collaborate with product and engineering to turn ambiguity into working software and will work directly with the founders. This is a full-time hybrid role requiring regular in-person collaboration at the Los Angeles office. Candidates must be authorized to work in the country where the role is based; visa sponsorship is unavailable.

Requirements

  • At least 7 years of experience and a deep background building production software.
  • Deep practical experience with transformer-based technologies, including embeddings, vector databases, tool-calling, and context window management.
  • At least 2 years of experience shipping LLM-based products to real users in production.
  • Strong Python skills and the ability to build complete systems, not just notebook experiments.
  • Ability to identify LLM and agent failure modes, such as hallucinations, API timeouts, and infinite loops, and build guardrails against them.
  • A security mindset that treats access to enterprise data as part of system design.
  • Clear communication skills and a founder-level ownership mindset.
  • Authorization to work in the country where the role is based; visa sponsorship is not available.

Nice To Haves

  • Experience building complex, multi-step workflows with frameworks such as LangGraph, LlamaIndex, or PydanticAI.
  • Hands-on experience with fine-tuning and PEFT methods such as LoRA or QLoRA to adapt open-weight models for domain-specific tasks.
  • Experience with human-in-the-loop workflows and enterprise identity systems, including SSO and role-based access.
  • Background in enterprise operations, such as industrial, logistics, fintech, or CRM workflows.
  • Strong opinions about where AI creates value and where it is expensive noise.

Responsibilities

  • Design, prototype, and harden production-grade orchestration frameworks using LLMs, persistent memory, and tool integration for complex enterprise tasks.
  • Implement RAG pipelines to retrieve high-fidelity context from fragmented data sources.
  • Build internal benchmarking and evaluation suites to measure and improve model reliability, grounding, and latency.
  • Architect intelligence stacks that pragmatically combine frontier reasoning models, fine-tuned open-weight models, and deterministic heuristics.
  • Partner with product and engineering to turn ambiguity into working software.
  • Work directly with the founders and ship impactful systems quickly.

Benefits

  • Health insurance.
  • Retirement plans.
  • May qualify for participation in the Company’s bonus and incentive programs.
© 2026 Teal Labs, Inc
Privacy PolicyTerms of Service