At Immigrant Invest, we combine advanced technology with deep expertise in investment migration, helping clients obtain citizenship and residency quickly and transparently.
Because we work with passports, financial documents, and due diligence materials, reliability, security, and privacy are fundamental engineering requirements — not afterthoughts.
We value ownership, practical engineering, and shipping AI systems that create measurable business impact.
We’re looking for an AI Engineer who can turn production AI prototypes into reliable, scalable systems. You’ll own the architecture, implementation, deployment, and operation of AI agents that are already delivering business value — not experimenting in a lab.
If you enjoy building production-grade LLM systems, solving complex orchestration challenges, and taking full ownership of AI products, we’d love to meet you.
What You’ll Do * Rebuild our AI content generation pipeline into a scalable multi-agent architecture with checkpointing, fault recovery, and parallel execution. * Bring our customer-facing WhatsApp RAG agent to production-grade reliability through retries, rate-limit handling, deduplication, and observability. * Design and implement analytics for the customer journey by integrating Salesforce data into a unified event model. * Launch an AI-powered quality auditing agent for customer managers. * Design a private AI environment for processing sensitive customer documents using Azure and/or local LLMs. * Build evaluation frameworks that measure AI agent quality and performance. * Improve architecture, reliability, monitoring, documentation, and developer experience across our AI ecosystem.
What We’re Looking For * 4–6+ years of software engineering experience. * At least 1 year building and operating production LLM applications. * Strong Python engineering skills, including: * asynchronous programming * project architecture * testing * Experience designing production services rather than scripts or prototypes. * Experience with agent frameworks and orchestration (LangGraph). * Experience communicating with business stakeholders and translating ambiguous business problems into technical solutions. * Advanced English & Russian
Nice to Have * Experience with local LLM deployment (vLLM, Ollama, quantization). * Experience designing AI infrastructure handling sensitive or regulated data. * Familiarity with agent frameworks and orchestration (LangGraph). * Experience working in small, fast-moving engineering teams. * Exposure to n8n, Make, or similar automation platforms.
What Success Looks Like During your first months you will: * Become productive within our AI infrastructure. * Successfully launch one or two production AI agents. * Deliver the first stage of a redesigned content generation architecture. * Introduce automated evaluation for at least one AI agent. * Document your work so another engineer can easily continue development.
You’ll Be a Great Fit If You * Think like an engineer rather than a prompt designer. * Have built AI systems that real users relied on. * Enjoy owning projects from architecture through production. * Can explain technical decisions and trade-offs clearly. * Know when not to use an LLM.
You’ll Probably Not Enjoy This Role If * Your experience is limited to prompt engineering or chatbot demos. * You’re primarily interested in AI research or model training. * You prefer working exclusively on Python and are unwilling to touch low-code systems during the transition period. * You’ve never supported production systems or handled incidents. * You’re uncomfortable taking operational ownership.
What We Offer? * Your work will immediately impact products already serving paying customers. * Own the full engineering lifecycle — from architecture to deployment. * Small, fast-moving team with rapid decision making. * Budget to use the right AI models for the job. * Opportunity to build a private AI infrastructure from the ground up. * Clear technical challenges with measurable impact.
Why Join Immigrant Invest? Make a Global Impact: Help build automation systems that support a global company assisting individuals and families in obtaining second citizenship and residency. Your work will directly improve operational efficiency and customer experience.
Empowerment & Autonomy: We trust our team members. You will have the flexibility to work remotely and manage your own schedule, giving you the autonomy to structure your day for peak productivity.
Commitment to Growth: We invest in your professional development. You’ll have access to continuous learning opportunities through on-the-job training, external conferences, and dedicated coaching sessions. We also offer stretch assignments to help you grow your skills and career.
Open & Collaborative Culture: We value ownership, transparency, and continuous improvement. You’ll work closely with experienced engineers in a supportive environment where learning and sharing knowledge are part of everyday work.
If you’re excited about building reliable AI-powered automation systems and want to grow quickly in a fast-moving environment, we’d love to hear from you.
