golang engineer for LLM platforms

EPAM is building a comprehensive platform that evaluates Large Language Model performance and provides inference endpoints for Generative AI applications at enterprise scale. The platform assesses, compares, and governs LLM inference across multiple model providers for use cases including natural language processing, customer service automation, content generation, and data analysis.

• Design and implement production-grade backend features using Go in a microservices-style architecture;
• Build and maintain provider integration frameworks for external LLM vendors, including OpenAI, Anthropic, and cloud AI services;
• Own backend service quality through unit and integration testing and continuously improve CI/CD quality gates;
• Improve data access reliability and performance across PostgreSQL and Redis;
• Collaborate cross-functionally on architecture, scalability, security, and operational excellence;
• Lead technical design discussions and deliver solutions independently end-to-end;
• Work with product teams on API requirements, troubleshoot issues, and identify new requirements;
• Contribute technical input to the platform roadmap, including feasibility, trade-offs, and system design.

• 7+ Years of professional software engineering experience with strong backend ownership;
• Deep expertise in Go, including idiomatic design, interfaces, concurrency, context management, and error handling;
• Hands-on experience building HTTP APIs, middleware, and service-oriented architectures;
• Strong experience with PostgreSQL, including schema design, query optimization, and database migration workflows;
• Practical experience with Redis, including caching strategies, counters, and distributed rate-limiting patterns;
• Experience designing or working with authorization and policy systems, including RBAC/ABAC concepts;
• Strong testing discipline in Go, including table-driven tests, mocks, integration tests, and test containers;
• Experience operating production systems with observability tooling, including OpenTelemetry metrics and tracing, dashboards, and alerting;
• Solid experience with Kubernetes and Helm deployments;
• Strong CI/CD experience with GitHub Actions or equivalent;
• Demonstrated ability to lead technical design and execute independently;
• Familiarity with GenAI concepts and OpenAI APIs, with a drive for self-learning;
• Familiarity with AI-assisted development while maintaining strong quality and architectural standards;
• Good communication and collaboration skills;
• B2+ English level, written and verbal;
• Nice to have: experience building LLM gateways, API gateways, or multi-provider AI/ML integration platforms, experience with gRPC, cloud SDKs, or service integrations on AWS, Azure, or GCP, familiarity with API platform security controls including API keys, OIDC, secrets management, and abuse prevention, exposure to cost and performance optimization for high-volume inference or request-processing workloads, experience contributing to platform roadmap planning including epics, user stories, and backlog prioritization, background working with UX/product teams during early-stage platform definition.

• No conditions specified