3 дня назад
Senior Backend Engineer - AI Platform
Мэтч & Сопровод
Для мэтча с этой вакансией нужен Plus
Описание вакансии
Текст:
TL;DR
Senior Backend Engineer - AI Platform (Python/AI): Building a centralized, high-throughput AI platform with an accent on agent runtimes, distributed tool and data pipelines, low-latency model gateways, and real-time evaluation and observability systems. Focus on designing resilient core services, optimizing distributed execution and latency, and implementing secure, fault-tolerant infrastructure for high-volume AI workflows.
Location: Prague, Czech Republic; hybrid model with 3 days in the office and 2 days working from home.
Company
provides digital intelligence data and solutions that help businesses understand online activity and make data-driven strategic decisions.
What you will do
- Architect and build a high-availability AI agent platform with distributed orchestration, persistent state and memory, event-driven execution, and a high-performance Python SDK.
- Design scalable tool and connector services, including MCP servers, gRPC and REST endpoints, and secure integrations with internal data stores, microservices, and external APIs.
- Build low-latency model gateways with connection pooling, automated failover routing, semantic caching, and rate limiting.
- Implement zero-trust platform security, including fine-grained access control, isolated data boundaries, PII detection pipelines, and audit logging.
- Optimize distributed execution for SLA compliance, lower latency and compute costs, and reliable observability through distributed tracing and custom metrics.
Requirements
- 5+ years of backend software engineering experience with advanced Python skills and backend system architecture expertise.
- Experience building asynchronous microservices, REST and gRPC APIs, distributed state management, containers, and CI/CD pipelines.
- Hands-on experience building or extending agentic runtime frameworks such as LangGraph or LangChain.
- Knowledge of SQL, NoSQL, and vector databases, Redis caching, and event-driven messaging with Kafka or RabbitMQ.
- Ability to design clear API contracts and developer-facing platform tooling for engineering teams.
Nice to have
- Experience with AWS, Kubernetes, Terraform or CloudFormation, and cloud-native deployment patterns.
- Expertise in LLMOps, model routing, load balancing, capacity planning, and cost and latency optimization.
- Experience designing retrieval-augmented generation pipelines over large-scale, heterogeneous data lakes.
- Experience with distributed tracing and custom APM dashboards.
Culture & Benefits
- Hybrid work model with three office days and two home-working days per week.
- Five weeks of vacation, a birthday day off, three sick days, and a Multisport option.
- Modern Prague office with snacks, drinks, fruit, and Tuesday lunches.
- MacBook Pro, dual monitors, and standing desks.
- Equity, team events, and career development through coaching and learning programs.
Будьте осторожны: если работодатель просит войти в их систему, используя iCloud/Google, прислать код/пароль, запустить код/ПО, не делайте этого - это мошенники. Обязательно жмите "Пожаловаться" или пишите в поддержку. Подробнее в гайде →