Backend AI Engineer

Job Overview

Jedify is redefining data intelligence. Trusted by enterprise customers, we enable true actionable insight through Agentic interfaces (chat, research, MCP) built on top of our proprietary Semantic Fusion Model (SFM). We’re seeking an exceptional Senior Backend Engineer with deep knowledge and experience in Gen AI to join our team. You’ll architect and build our production-grade agents that powers intelligent data analysis and semantic capabilities for enterprise customers. This role combines backend engineering with Gen AI – perfect for engineers who want to push the boundaries of what’s possible with modern AI technology.

What You’ll Build

Production GenAI components that power our agent – each processes and analyzes enterprise semantics using multiple LLM providers.
Robust context engineering platform for managing and optimizing GenAI workflows at scale
High-performance reliable backend architecture.

Requirements

Strong problem-solving mindset with ability to tackle complex technical challenges.
Autonomous player who can take ownership and drive solutions independently.
Overall 8+ years in software engineering with startup experience.
5+ years backend engineering experience with expert Python skills.
1+ years production generative AI experience with LLMs and prompt engineering. A must.
Experience with scalable backend systems, micro-services, and distributed systems.
AWS experience: EKS, S3, Bedrock, Elasticache, RDS.
Production system experience: monitoring, alerting, security.
Super important – Get shit done attitude, curiosity, and pro-active mindset.
Tech Stack:
Python 3.11+, FastAPI, MongoDB, PostgreSQL, Redis, LiteLLM, AWS, Docker, K8S, Helm
Dev Stack:
Cursor, Claude Code, Warp

Apply for this position

Here’s Why Context Graphs Are the Next Must-Have for Enterprise AI

Backend AI Engineer