Go (Golang) Backend Engineer (AI/LLM, RAG) Middle–Senior
SoftBee · Remote
25 / Hour · Posted Nov 19, 2026
Apply to this job with Jobrona
Create your account and upload your CV. If this job fits it, we prepare and send this application first, and show you exactly what was sent.
About the job
Rate: Up to $25/hour
Employment: Full-time or part time >25h/week
Duration: 6-8 months
Start: In 2-3 weeks
English: B2
We are looking for an experienced Go Backend Engineer with a strong interest in AI technologies and hands-on experience building scalable backend systems.
You will work on modern AI-powered products, integrating Large Language Models (LLMs), building intelligent workflows, and developing reliable backend infrastructure for AI-driven applications.
We are looking for an engineer who combines strong backend fundamentals with a practical understanding of AI engineering and knows how to turn AI capabilities into real production features.
Tech Stack
Backend: Go (Golang), REST API, gRPC, Microservices, PostgreSQL, Redis
AI: OpenAI, Anthropic Claude, Gemini, LLM APIs, RAG, Embeddings, Vector Search, AI Agents
Infrastructure: AWS, Docker, Kubernetes, CI/CD, GitHub Actions
Additional: Python, pgvector, Qdrant, MCP, LangChain/LangGraph
Requirements
- 3+ years of commercial backend development experience, including 2+ years with Go (Golang).
- Strong knowledge of Go, including goroutines, channels, concurrency patterns, context management, and performance optimization.
- Experience designing, developing, and maintaining production-ready backend services and APIs.
- Strong understanding of REST API, gRPC, microservices architecture, and asynchronous processing.
- Hands-on experience with PostgreSQL, Redis, and database performance optimization.
- Experience with Docker, CI/CD pipelines, and cloud infrastructure (preferably AWS).
- Solid understanding of software architecture, clean code principles, testing, and system reliability.
- Practical experience integrating LLM APIs (OpenAI, Anthropic, Gemini, or similar) into backend applications.
- Understanding of prompt engineering, structured outputs, function/tool calling, and LLM limitations.
- Familiarity with RAG architecture, embeddings, vector databases, and semantic search.
- Understanding of AI application performance, latency, token usage, and cost optimization.
- English: B2 Intermediate+.
Nice to Have
- Experience developing AI agents, agentic workflows, or multi-step LLM orchestration.
- Experience with Model Context Protocol (MCP) and building integrations between AI agents and external tools.
- Hands-on experience with vector databases (Qdrant, Pinecone, Weaviate, pgvector).
- Knowledge of advanced RAG techniques: hybrid search, reranking, chunking strategies, and retrieval optimization.
- Experience with Python for AI integrations, automation, or ML-related services.
- Familiarity with LangChain, LangGraph, LlamaIndex, or similar AI orchestration frameworks.
- Experience with LLM evaluation, tracing, observability, and guardrails.
- Understanding of AI security, prompt injection risks, and data privacy.
- Experience working with open-source LLMs or self-hosted inference solutions.
- Experience building high-load or distributed systems.
Responsibilities
- Design, build, and maintain scalable backend services using Go.
- Develop and integrate AI-powered functionality using modern LLM providers.
- Build backend components for RAG pipelines, semantic search, and intelligent data processing.
- Implement AI agent workflows, tool integrations, and automation capabilities.
- Optimize backend performance, reliability, scalability, and infrastructure costs.
- Improve LLM response quality, latency, and token efficiency.
- Collaborate with product and engineering teams on architecture and technical decisions.
- Write clean, maintainable, well-tested code and participate in code reviews.
- Contribute to the technical evolution of AI-powered products.
What We Value
- Strong engineering fundamentals and a product-oriented mindset.
- Real production experience rather than only experimental AI projects.
- Ability to independently own backend features from design to deployment.
- Curiosity about AI technologies and willingness to explore emerging tools.
- Pragmatic problem-solving and an understanding of technical trade-offs.
If you enjoy building reliable backend systems and want to work at the intersection of Go, AI, and modern software architecture, we'd love to hear from you!