AI Specialist — LLMs (2–3 Years Experience)
You’ll help build and ship AI features inside Ledgers—turning LLM capabilities into reliable product workflows for founders.
Apply for this role
Send your CV + a short note. We’ll reply if it’s a fit.
About Us
Ledgers is building an AI-powered Financial Operating System for founders and business leaders.
We focus on clarity, control, and decision-making—bringing financial logic into a product founders can operate day-to-day.
We’re assembling a lean, high-quality team to build the next phase of the product.
Job Description
This is a Lebanon-based remote role.
You will design, prototype, and productionize LLM-powered workflows across product surfaces (insights, classification, retrieval, forecasting support, and internal tools).
You’ll work closely with engineering and product to balance accuracy, latency, cost, and safety—shipping features that are measurable and dependable.
Responsibilities
- Design and ship LLM features end-to-end (prompting, tooling, evaluation, iteration)
- Build retrieval workflows (RAG) with embeddings, chunking, ranking, and caching
- Define evaluation methodology (golden sets, offline tests, online metrics) and track quality over time
- Optimize for latency and cost (model choice, batching, caching, truncation strategies)
- Implement guardrails: safe completion patterns, fallbacks, and failure handling
- Collaborate with product to translate user needs into AI specs and acceptance criteria
Requirements
- 2–3 years of hands-on experience building LLM or NLP features (production preferred)
- Strong Python skills and familiarity with common LLM tooling (OpenAI/Anthropic APIs, LangChain/LlamaIndex or similar)
- Solid understanding of embeddings + retrieval (vector DBs, chunking strategies, reranking)
- Experience designing evaluations (datasets, scoring, regressions) and iterating based on results
- Comfortable working with APIs, backend services, and data pipelines (not only notebooks)
- Clear communication and ownership mindset in a fast-moving environment
Nice to have
- Experience with function calling / tool-use patterns
- Experience with structured outputs (JSON schemas) and reliability techniques
- Awareness of privacy/security practices when handling user/business data
- Exposure to fintech/accounting concepts (helpful, not required)
Benefits
- Remote-first (Lebanon-based)
- Direct collaboration with leadership and core product team
- Ownership and high impact from day one
- Growth path as the AI surface area expands
- ESOP consideration for early hires