Backend Engineer (Gen AI)
Summary
Designs and builds backend APIs and services for a Gen AI platform using Python, FastAPI, PostgreSQL, Redis, and AWS, integrating LLM APIs (OpenAI, Anthropic, Bedrock) and implementing RAG, vector search, and caching for AI workloads.
Compensation: ₹1.2L – ₹1.8L • No equity
About Us We're a fast-moving startup building innovative Gen AI solutions that scale. We're looking for a talented backend engineer who thrives in a dynamic environment and wants to make a real impact in the AI space.
The Role We're seeking a Backend Engineer with Gen AI expertise to design, build, and maintain the core systems that power our AI-driven platform. You'll work closely with our product and engineering teams to create robust, scalable APIs and services that integrate cutting-edge language models and deliver exceptional performance.
What You'll Do
- Design and develop RESTful APIs using Python and FastAPI for AI-powered applications
- Integrate and optimize LLM APIs (OpenAI, Anthropic, AWS Bedrock, etc.)
- Build prompt engineering pipelines and manage context windows effectively
- Implement vector databases and semantic search capabilities
- Build and optimize PostgreSQL database schemas, queries, and migrations
- Implement and maintain authentication and authorization systems (JWT, OAuth 2.0, session management)
- Design and implement Redis caching strategies for LLM responses and high-performance data access
- Deploy and manage services on AWS (EC2, RDS, ElastiCache, S3, Lambda, Bedrock)
- Develop RAG (Retrieval Augmented Generation) systems and fine-tuning pipelines
- Implement streaming responses and async processing for AI workloads
- Monitor LLM performance, costs, and implement usage tracking
- Write clean, maintainable, and well-tested code
- Collaborate with frontend engineers to define API contracts and integration patterns
- Implement security best practices including rate limiting, input validation, and secure token management
- Participate in code reviews and contribute to engineering standards
What We're Looking For
- 1+ years of professional backend development experience
- Already completed graduation
- Strong proficiency in Python and modern async frameworks (FastAPI preferred)
- Hands-on experience integrating LLM APIs (GPT-4, Claude, Llama, etc.)
- Understanding of prompt engineering, context management, and token optimization
- Solid understanding of PostgreSQL, including query optimization and database design
- Experience with version control (Git) and collaborative development workflows
- Ability to write unit and integration tests
- Strong problem-solving skills and attention to detail
Nice to Have
Understanding of microservices architecture Experience optimizing LLM costs and implementing smart caching strategies
What We Offer
- Competitive salary and equity package
- Flexible work arrangements
- Modern tech stack and cutting-edge AI tools
- Opportunity to shape our technical direction in the AI space
- Fast-paced startup environment where your work matters
- Work on real-world AI applications that impact users