Senior Applied AI Engineer

lemlist; Paris; Hybride; EUR 120 000 - 180 000; Plein temps

Résumé du poste

lemlist is seeking an applied AI engineer to turn LLM insights into a reliable production product. You will own agent orchestration, context engineering, memory management, retrieval and evaluation in collaboration with software engineers and product teams.

You will focus on achieving the best quality/latency/cost trade-offs, ensure safety and guardrails, and relentlessly improve the AI product with new opportunities across the system.

Qualifications

• 10+ years of experience in software development or data science.
• Deep knowledge of LLM architecture, prompting, context engineering, and vector database workflows.
• Hands-on experience building agentic systems, using orchestration frameworks (e.g., LangGraph, Agno, Mastra, custom), and running evaluations.

Responsabilités

• Turn the raw intelligence of LLMs into a reliable product in production.

Connaissances

Software development

Data science

LLM architecture

Prompt engineering

Context engineering

Vector databases

Agent orchestration

Orchestration frameworks

Entrepreneurial experience

Outils

LangGraph

Agno

Mastra

Custom orchestration

Description du poste

The project

The SaaS industry is shifting from rigid UIs manually operated by humans to proactive systems built around in-depth domain expertise that deliver outcomes for users.

The sales automation software industry is at the center of this agentic revolution.

With thousands of customers using our platform every day and extensive proprietary data, lemlist is determined to chart the future of agentic AI for sellers.

We are building the AI-native agentic system that automates the heavy lifting of prospecting and pipeline generation and consistently improves at generating new business opportunities for our customers.

The role

As an applied AI engineer, you turn the raw intelligence of LLMs into a reliable product in production. Agent orchestration, context engineering, memory management, retrieval, and evaluation are at the center of your day-to-day work in collaboration with software engineers and product teams.

You are responsible for ensuring our system delivers the best possible outcomes for our customers. In practice:

• You consistently look for the best quality/latency/cost trade-offs.

• You own our evaluation and guardrails system ensuring reliability and safety.

• You own our context engineering system.

• You consistently improve our AI product by identifying and implementing new opportunities at every level.
  

What we are looking for:

Mindset

• You have an entrepreneurial mindset. You are a proactive doer, resilient, and accountable.

• Everyone talks to users! You are user-centric and excited about the real-world impact of your AI product.

• You have a deep curiosity for the AI space.

• You are fine with a high-speed, high-ambiguity environment. You are ready to embrace how fast things are moving in the Agent AI space.

• You consistently improve your agentic coding tool setup (Claude code, Codex,...)

Experience

• 10+ years of experience in software development or data science, engineering production systems using modern programming languages.

• Deep knowledge of LLM architecture, prompting, context engineering, and vector database workflows.

• Hands-on experience building agentic systems, using orchestration frameworks (e.g., LangGraph, Agno, Mastra, custom), and running evaluations.

• Entrepreneurial experience is a real plus.