Founding AI / LLM Engineer
Rethink recruit
·Today
- Type
- Full-time
- Department
- Engineering
- Experience
- 7+ years
- Source
- RecruiterFlow
Description
ABOUT SKIFFRA
Skiffra is building the intelligence layer for the physical world, translating complex, real-world environments into clear, actionable data.
While most AI companies focus on digital industries, Skiffra designs AI-native orchestration systems for the sectors that extract, move, and build the ecosystems around us. They turn messy, high-stakes operations into intelligent, adaptive workflows that improve decisions in real time.
Their first proving ground is mining and natural resources, but the platform is modular by design and built to scale into any industry where decisions are expensive and the consequences are real. The team is based in Los Angeles.
THE OPPORTUNITY
You will be the architect of Skiffra’s core intelligence, moving agentic workflows from concept to production-grade systems that handle real enterprise data at scale. This is a founding-level role for a high-leverage builder who moves fluidly between prompt engineering, backend systems, and model optimization.
WHAT YOU'LL DO
- Design, prototype, and harden production-grade orchestration frameworks that leverage LLMs, persistent memory, and tool integration to navigate complex, non-linear enterprise tasks
- Implement RAG pipelines that ensure high-fidelity context retrieval from fragmented data sources
- Build internal benchmarking and evaluation suites to measure and improve model reliability, grounding, and latency
- Architect high-performance intelligence stacks by making pragmatic tradeoffs between frontier reasoning models for long-horizon agentic planning, fine-tuned open-weight models for data sovereignty and low-latency inference, and deterministic heuristics for reliable, cost-efficient guardrails
- Work directly with founders to translate ambiguous operational problems into clean, scalable, AI-powered software
- Partner with product and engineering to turn ambiguity into working software
YOU SHOULD HAVE
- 7+ years of systems engineering experience building production software
- Deep practical experience with the transformer-based stack: embeddings, vector databases, tool-calling, and context window management
- Python fluency at the systems level, not just notebooks
- Strong instincts for failure modes such as hallucinations, API timeouts, and agent loops, and how to build guardrails against them
- Clear communication and a founder-level ownership mindset
NICE TO HAVE
- Experience building complex multi-step workflows using LangGraph, LlamaIndex, or CrewAI
- Hands-on experience with fine-tuning and PEFT techniques such as LoRA and QLoRA to adapt open-weight models for domain-specific tasks
- Background in enterprise operations including industrial, logistics, fintech, or CRM workflows
- Strong opinions on where AI creates value and where it doesn’t