- Company Name
- lemlist
- Job Title
- Senior AI Engineer
- Job Description
-
**Job Title:** Senior AI Engineer (Hands‑On)
**Role Summary:**
Design, build, and scale lemlist's AI architecture to transition from basic prompt calls to autonomous, multi‑step agentic systems. Own end‑to‑end AI engineering, from agent design to monitoring, and deliver product‑increasing AI features such as the Copilot v1.
**Expactations:**
- Deliver a production‑ready agentic architecture within 6 months.
- Build autonomous workflow loops that process leads, enrich data, and trigger actions.
- Deploy the first version of the Copilot feature with measurable business value.
- Establish global AI monitoring, evaluation, and bias mitigation practices.
- Foster an AI engineering culture through mentorship and documentation.
**Key Responsibilities:**
1. **AI Architecture** – Design and implement agentic frameworks (LangGraph, Mastra, custom JS).
2. **Context & Memory Management** – Define data flow, state machines, and action orchestration.
3. **Build Autonomous Agent Loops** – Enable AI variables that iterate over lists (e.g., for each lead).
4. **Copilot Development** – Create Semi‑Agentic Copilot v1; plan future autonomous extensions.
5. **Evaluation & Monitoring** – Build LLM evaluation pipelines, regression tests, drift detection, and 360‑degree monitoring (latency, cost, quality, hallucinations).
6. **Bias & Explainability** – Perform error analysis, improve models for fairness and transparency.
7. **Performance & Cost Optimization** – Continuously refine model efficiency.
8. **Documentation & Knowledge Sharing** – Record processes, results, and best practices.
9. **Collaboration & Enablement** – Work with Data Scientists, developers, PMs, and CPO; mentor peers; own AI technical direction.
**Required Skills:**
- Proficient in Node.js, TypeScript, and Python.
- Proven experience building production AI features at scale.
- Deep understanding of agentic systems, context/state‑machine logic, and Retrieval‑Augmented Generation.
- Skills in LLM evaluation frameworks and monitoring.
- Ability to own technical vision from conception to deployment.
- Strong leadership, communication, and critical‑thinking abilities.
- Passion for deploying real AI solutions and continuous learning.
**Nice to Have:**
- LangChain / LangGraph experience.
- LLM evaluation tools (Trulens, DeepEval, Opik, etc.).
- SaaS background, mentoring experience, open‑source contributions.
- Ability to translate complex AI concepts for non‑technical stakeholders.
**Required Education & Certifications:**
- Bachelor’s or Master’s degree in Computer Science, Engineering, or related field.
- No mandatory certifications required.