Backend Engineer (Gen AI)
Core
Design, build, and maintain core backend systems and APIs for a Gen AI platform, integrating language models and optimizing performance for AI-driven applications.
Role type
Backend Engineer (Gen AI)
Builds
Scalable APIs, RAG systems, and AI workloads for an AI-driven platform
Domain
Generative AI, Cloud Infrastructure
Deliverable
production ML models | product features | infrastructure
Required skills
Python, FastAPI, LLM API integration, Prompt engineering, PostgreSQL, Redis, AWS services, Authentication/Authorization, Unit testing
Preferred skills
Microservices architecture, LLM cost optimization
Technologies
Python, FastAPI, OpenAI, Anthropic, AWS Bedrock, PostgreSQL, Redis, AWS (EC2, RDS, ElastiCache, S3, Lambda), Git
Responsibilities
Design and develop RESTful APIs for AI applications, Integrate and optimize LLM APIs, Build prompt engineering pipelines, Implement vector databases and semantic search, Optimize PostgreSQL schemas and queries, Deploy and manage services on AWS, Develop RAG systems and fine-tuning pipelines, Monitor LLM performance and costs
Seniority
Junior to Mid-level, hands-on IC