ai engineer for enterprise AI platforms

Grid Dynamics provides technology consulting, platform and product engineering, AI, and advanced analytics services. The company helps enterprise organizations solve complex technical challenges and achieve business outcomes during business transformation.

• Lead and mentor a team of senior engineers, establish technical standards, conduct code reviews, and foster engineering excellence across the squad;
• Own the end-to-end architecture of the enterprise AI platform, including agent orchestration, tool execution, memory, retrieval, observability, identity, and authorization;
• Author Architecture Decision Records and make key decisions on data models, async patterns, caching, and deployment topologies;
• Design data isolation, identity, and access management for single-tenant customer-cloud installations and scaling to managed multi-tenant offerings;
• Architect integrations with WorkOS and Cerbos;
• Architect enterprise guardrails, prompt-injection defenses, PII redaction, and output validation pipelines;
• Drive cost discipline, model routing, token budgeting, and caching strategies while ensuring agent decisions are auditable, traceable, and defensible;
• Personally lead challenging technical work involving distributed systems edge cases, performance investigations under load, online migrations, and security architecture;
• Write high-quality Python code;
• Partner with Product leadership to translate roadmaps into coherent, on-time engineering commitments;
• Serve as the primary technical authority in customer discussions, CISO security reviews, and architecture deep-dives;
• Partner with Forward Deployment leads on deployment topologies.

• 8+ Years of commercial software engineering experience;
• Proven experience in a Tech Lead, Team Lead, or Principal Engineer capacity leading complex distributed systems or AI projects;
• Proven experience shipping and operating LLM-based applications at scale;
• Expert-level prompt engineering, advanced RAG, tool-using agent frameworks, prompt-injection defense, evaluation pipelines, and cost/latency management;
• Deep expertise in shipping multi-tenant products and understanding trade-offs across shared-everything, shared-database, and isolated single-tenant or silo deployments;
• Strong foundation in distributed systems, including idempotency, eventual consistency, queue-based async, and distributed locking;
• Strong security architecture knowledge, including end-to-end authn/authz, OWASP mitigation, RBAC, and ABAC;
• Advanced Python proficiency;
• Working knowledge of TypeScript and Node.js;
• Strong PostgreSQL expertise under heavy load, including pool tuning, indexing, online migrations, and pgvector or vector stores;
• Strong AWS expertise and working knowledge of Azure or GCP;
• Exceptional team leadership and mentoring abilities;
• Strong written and verbal English communication skills for working with cross-functional partners and senior executive stakeholders.

• Competitive salary;
• Flexible schedule;
• Medical insurance and sports benefits;
• Corporate social events;
• Professional development opportunities;
• Well-equipped office.