AI Engineer
Spektr provides an AI-powered platform for automating compliance operations, including onboarding, monitoring, document checks, ownership mapping, risk analysis, and remediation. Its customers include fintechs, banks, and financial institutions.
Funding history
Projects
About Spektr
Spektr offers a complete compliance operations platform combining AI agents and configurable processes. Its AI agents execute tasks such as KYB, document review, ownership mapping, source-of-funds analysis, website checks, and false-positive reduction, while connected workflows collect data, trigger checks, update records, and automate follow-up actions across onboarding, monitoring, risk, remediation, enrichment, questionnaires, and scoring. Spektr serves fintechs, enterprise banks, and other financial institutions, with case studies involving payments, crypto-wallet, digital banking, leasing, and EV-charging businesses.
Skills
Candidate Availability
Required and preferred rules are kept separate and reflect the wording in the original posting.
About the Role
You own the end-to-end AI roadmap, select and integrate models, and design and deploy LLM-powered features such as autonomous agents, RAG pipelines, and intelligent document understanding. You translate compliance problems into scalable AI solutions, monitor AI and ML research, and make AI outputs accurate, explainable, reliable, and resistant to hallucinations.
Requirements
- 2+ years of experience in ML, AI, or data/backend roles
- Deep understanding of modern LLM stacks
- Strong TypeScript and/or Python skills
- Hands-on experience with LangChain or equivalent orchestration layers
- Experience building production-grade RAG pipelines
- Understanding of embeddings, retrieval strategies, and re-ranking
- Experience setting up evaluation frameworks for model performance
- Experience deploying AI services in AWS or containerized environments
- Ability to communicate model architecture trade-offs and technical bottlenecks clearly
Responsibilities
- Own the end-to-end AI roadmap
- Select and integrate commercial or open-source models into the product
- Design and deploy autonomous agents, RAG pipelines, and intelligent document-understanding features
- Translate compliance problems into scalable AI solutions
- Monitor AI and ML research, papers, and releases
- Ensure AI agents are accurate, explainable, reliable, and resistant to hallucinations
