AI Engineer - Build Next-Gen Compliance Agents
Role details
Job location
Tech stack
Job description
for an AI Engineer who is, first and foremost, a product builder . In this role, you won't just be running experiments in a notebook; you will own the end-to-end AI strategy and its direct impact on our customers. In this role, you will own everything related to AI, LLMs, and intelligent automation. This is a high-impact role in a fast-growing company. We are looking for someone who thrives in a dynamic environment, loves solving complex compliance puzzles, and is eager to shape the next generation of compliance technology. What You Will Be Doing AI Strategy & Ownership: Own the end-to-end AI roadmap-from selecting the right models (SOTA commercial vs. fine-tuned open source) to deciding how they are integrated into the product core. Agentic Feature Design: Design and deploy LLM-powered features including autonomous agents, advanced RAG pipelines, and intelligent document understanding. Product-Led AI: Collaborate directly with founders to translate complex compliance "puzzles"
Requirements
into scalable AI solutions. You own the "Why" behind every model choice. Continuous Innovation: Stay at the bleeding edge of AI/ML research, proactively identifying new papers or releases that can give spektr a competitive advantage. Engineering for Reliability: Turn non-deterministic AI outputs into deterministic product value. You ensure our agents are accurate, explainable, and hallucination-free. What We Are Looking For The Product Mindset: You are a product person at heart. You care about whether the AI actually solves the user's problem, not just if the loss curve is going down. High-Agency Builder: You prefer building systems over following manuals. You identify bottlenecks in our AI workflows and fix them before they become tickets. AI/ML Expertise: 2+ years of experience in ML, AI, or Data/Backend roles with a deep understanding of modern LLM stacks. Technical Mastery: Strong skills in TypeScript (our core) and/or Python , with hands-on experience in frameworks like LangChain or equivalent orchestration layers. RAG & Vector Mastery: You've built production-grade RAG pipelines and understand the nuances of embedding, retrieval strategy, and re-ranking. Evaluation Obsession: You understand that "it works on my machine" doesn't apply to LLMs. You have experience setting up evaluation frameworks to measure and improve model performance. Cloud & Scale: Experience deploying AI services in AWS or containerized environments, ensuring they are scalable and cost-effective. Communication: You can explain the trade-offs of a specific model architecture to a founder and a technical bottleneck to a peer with equal clarity. What We Offer Models: OpenAI, Anthropic, Google Gemini, and Open Source (LLaMA, Mistral). Stack: TypeScript, Python, LangChain, etc. Infra: AWS, Kubernetes, CI/CD for LLMs. What WE Offer An exciting opportunity to build the next generation of AI agents in a well-funded start-up. Work directly with our founders to build spektr from an early stage. Work with a team that enables, supports, and challenges you. Leverage our network of leading investors, partners and advisors in Europe and the U.S. Our Process Phone Screen (20 minutes) Technical Interview (30 minutes) Technical Interview (60 minutes) How To Apply We hire the smartest, kindest, and most unrelenting people and let them do their best work. You'll be joining a team with a proven track record and the "Product-Market Fit" to change an entire industry. Apply Here