AI Engineer Junior – Python / FastAPI / Langchain

AI Engineer – Full-time – Paris (Hybrid possible)

Company: MincaAI

Start: September

About us

MincaAI builds vertical AI agents for the insurance industry. Our technology powers custom agents for underwriting automation, claims handling, market intelligence, and sales qualification. We’re building the infrastructure to scale expert-level LLMs across regulated B2B sectors.

The role

We’re hiring an AI Engineer to help design, build, and ship production-ready agents powered by LLMs. You’ll work with the CTO and the tech team composed of AI engineers + Full-stack devs and be responsible for transforming client needs into working AI products. You’ll contribute across the entire stack—from RAG pipelines to fine-tuning and evaluation frameworks.

What success looks like

• You’re autonomous in building multi-agent chains and can deploy scalable prototypes within 3 months
• You contribute to our technical roadmap with model optimizations and new R&D features
• You help bridge research and client delivery by turning cutting-edge methods into useful solutions

Responsibilities

• Build agent workflows using LangChain, RAG, and external tool integrations
• Fine-tune LLMs for specific business use cases (LoRA, PEFT, OpenAI, Claude, Mistral…)
• Contribute to evaluation, performance optimization, and feedback loops
• Work with backend and product teams to deploy and iterate quickly

Requirements

• 2+ years of experience in ML/AI (or equivalent projects)
• Strong Python skills and familiarity with LLM APIs and LangChain
• Knowledge of retrieval systems and vector databases (e.g., Weaviate, Pinecone)
• Bonus: experience in FastAPI, Docker, Streamlit, or regulated domains (insurance, health, legal)

Why join

• High-impact projects with fast iteration
• Tech-first environment with autonomy and fast decision-making
• Core position in a fast-growing AI company based in Paris

To apply, email us at [email protected] with your resume and link to your github !