AI Engineer

Formel AI combines the creativity of generative AI with the reliability of formal methods. Leveraging verification capabilities such as Lean 4, we pioneer a new generation of LLMs that are reliable, transparent, and cost‑efficient. In Nov 2025, we received the 2nd spot of the Innovation Prize from École normale supérieure. Formel AI is founded by Sylvain Combettes (CEO) and Antoine Mazarguil (CTO), who met during their PhDs at ENS Paris‑Saclay. In Feb 2026 we closed an oversubscribed angel round backed by over 30 top‑tier angel investors.

Address: Formel AI, 75000 Paris, France.

About The Role

As our AI Engineer, you will be at the forefront of AI innovation, working on groundbreaking technology that combines large language models with formal verification methods. You'll join a founding team of deep‑tech experts tackling one of the most critical challenges in AI: building LLMs that are transparent, reliable, and cost‑effective.

Role description: A hands‑on research and engineering role where you design and develop the next generation of formally verified AI systems. You will work on novel architectures, orchestration protocols, and training methodologies that eliminate hallucinations while dramatically reducing computational costs. You will join at a critical inflection point—moving from research breakthroughs to real‑world deployment with design partners in high‑stakes domains like healthcare and enterprise software, where AI reliability is non‑negotiable.

Key Responsibilities

• Design and develop AI systems: Lead the architecture and implementation of LLMs integrated with formal verification methods
• Build orchestration protocols: Design and implement orchestration frameworks, including tool calling, structured generation, and verification workflows
• Drive research innovation: Actively shape the company's research roadmap, exploring new architectures, training methodologies, and verification techniques in collaboration with our scientific advisory board
• Deploy with design partners: Work closely with 2‑3 early customers in high‑stakes domains to implement proof‑of‑concept solutions that demonstrate measurable improvements in AI reliability and cost‑efficiency
• Optimize training and evaluation: Develop advanced dataset generation pipelines, fine‑tuning workflows (DPO, RLHF), and rigorous evaluation protocols to continuously improve model performance
• Build reusable infrastructure: Create documentation, code templates, and engineering best practices that enable the team to scale our deployment approach as we grow
• Bridge theory and practice: Translate cutting‑edge research in AI into production‑grade systems

What we are looking for

Essential qualities

• Research‑driven curiosity: Passionate about exploring novel AI applications and architectures, pushing the boundaries of what’s possible
• Hands‑on technical excellence: Able to design, implement, and deploy production‑grade AI systems autonomously, from model training to orchestration
• Deep technical expertise: Strong knowledge of LLM architectures, training methodologies, and inference optimization
• Bridge builder: Translate complex research concepts into practical implementations

Background

• 3+ years of hands‑on experience building and deploying AI/ML systems, with deep expertise in Python, LLM APIs, and cloud infrastructure
• Strong foundation in machine learning fundamentals, model architectures, and modern AI engineering practices
• Deep knowledge of the latest developments in AI research and production systems

Required Skills

• Python mastery: Write clean, efficient Python code and understand object‑oriented programming principles deeply
• Fullstack fundamentals: Understand both frontend and backend development principles; can work across the stack when needed; proficient in Python for backend systems
• LLM expertise: Hands‑on experience with large language models, including API integration, prompt engineering, and orchestration frameworks
• LLM inference packages: Practical experience with at least one major LLM inference framework (vLLM, llama.cpp, TensorRT‑LLM, or similar) and understanding of inference optimization techniques
• Training & fine‑tuning: Implemented fine‑tuning workflows (DPO, RLHF, or similar) and understand dataset generation and model evaluation
• Model architectures: Deep knowledge of transformer architectures and modern inference optimization techniques
• Production experience: Deployed AI systems in production environments and understand the full ML lifecycle from training to deployment
• Research mindset: Stay current with the latest AI research and can quickly prototype and validate new ideas

Benefits

• Financial & perks
• Competitive cash salary and equity (BSPCE) in a high‑potential company
• Health insurance (Alan) for you and your family (partner and kids)
• Daily lunch vouchers (Swile)
• Hybrid work model with a strong emphasis on in‑office collaboration (typically 3‑4 days per week at the office) to foster team cohesion, spontaneous discussions, and deep work together
• Founding team impact: Join as one of the first employees and shape the trajectory of a moonshot deep‑tech company
• Mission‑driven startup: Help solve the key pressing challenges of AI—the most transformative technology of our era—ensuring LLMs are trustworthy, transparent, and cost‑effective, with direct benefits for environmental sustainability
• Work with cutting‑edge technology: Build systems that combine LLMs with formal verification—an emerging field at the forefront of AI safety and reliability where breakthrough developments happen every week
• World‑class team: Collaborate with a scientific advisory board from leading institutions and experienced business angels from top tech companies
• Strategic customers: Work with leading companies in healthcare, enterprise software, and other mission‑critical domains
• Flexibility of an early‑stage startup: Autonomy to define how you work and what you prioritize

Hiring process

• Apply and submit your resume using this Google Form
• Screening call (30 min): A quick chat with the CTO to align on vision and expectations
• In‑depth technical discussion (home exercise followed by a 60 min discussion): Best way to decide if we are a great fit as potential collaborators
• Technical deep‑dive (60 min): Focus on your proficiency with the tools you will use
• Founder interview (45 min): Final discussion on strategy, culture fit, and your long‑term evolution within the company, with the CTO and CEO