AI Backend Engineer

Its Partner — Kazakhstan · Posted ~3 hours ago

Mid Full-time

Skills

Python 3.12+ FastAPI asyncio WebSocket REST APIs AWS Bedrock LLM integrations Streaming APIs Tool/function calling AI agent workflows RAG MCP Prompt engineering LLM fundamentals Automated testing LLM evaluations Guardrails Docker CI/CD AWS Kubernetes Helm REST Anthropic Claude API OpenAI API Google Gemini API

🔓 Log in to save this job, tailor your resume & track your apply process — 7 days free, no card needed.

Log in to add to target list

Summary ✨ AI‑Generated

Build reliable production AI backend services using modern Python technologies and cloud-based LLM platforms. You will develop APIs and asynchronous services, integrate language models and agent workflows, implement RAG and context management, and establish testing, evaluation, guardrails, and scalable infrastructure practices.

Highlights

Production-focused AI backend role combining modern Python engineering with LLM integrations, agent workflows, retrieval, evaluation, and cloud infrastructure. Offers exposure to real-time systems, AI tooling, automated quality practices, and scalable infrastructure.

Description

What We Are Looking For Backend: Python 3.12+, FastAPI, asyncio, WebSocket, and REST APIs. Experience with gRPC is a plus.LLM integrations: AWS Bedrock experience is required; or/and familiarity with Anthropic Claude API, OpenAI API, and Google Gemini API, Vertex AI, etc. Experience with streaming APIs, tool/function calling, and multi-step agent workflows.AI tooling: RAG, MCP, prompt engineering, context enrichment, conversation history management, and external API integrations.ML/LLM fundamentals: At least basic nderstanding of transformers architecture and attention mechanisms, tokenization, embeddings, context windows, and data pipeline fundamentals.Quality and infrastructure: Automated testing, mocking external services, LLM evaluations and guardrails; Docker, CI/CD, AWS, and basic familiarity with Kubernetes/Helm.Nice to have: Real-time audio streaming, Gemini Live, ElevenLabs TTS/STT, AWS Connect, DynamoDB, MQTT, and IoT integrations.The role focuses on reliable production AI systems, not training models from scratch. Alternative Language Backgrounds Python is our primary implementation language, but prior Python expertise is not a strict requirement. We also welcome strong engineers whose main background is in:C++ – systems engineering, concurrency, networking, and performance.Go – backend services, cloud infrastructure, and gRPC.Java / Kotlin – production backend systems and service integrations.C# / .NET – asynchronous APIs and cloud applications.Rust – systems programming, asynchronous networking, and reliability.TypeScript / JavaScript (Node.js) – API development, asynchronous services, and LLM integrations.