Backend Engineer – GenAI / AWS Certified

We are looking for a Backend Engineer with strong expertise in Generative AI application development, including prompt engineering and context engineering, along with solid experience in AWS cloud services. The candidate will work on building scalable, secure, and high-performance GenAI-driven backend systems.

Key Responsibilities - Design and develop backend services for GenAI-powered applications (chatbots, RAG systems, automation workflows).

• Implement and optimize prompt engineering and context engineering strategies for LLM-based applications.
• Build and manage APIs using frameworks like FastAPI / Node.js.
• Integrate with LLM providers (AWS Bedrock, OpenAI, Anthropic, etc.).
• Develop scalable pipelines for document ingestion, embeddings, and retrieval (RAG).
• Work with vector databases (FAISS, Pinecone, OpenSearch, etc.).
• Ensure system performance, scalability, and reliability in production.
• Collaborate with frontend, AI/ML, and DevOps teams for end-to-end delivery.

Required Skills - Strong backend development experience in Python or Node.js.

• Hands-on experience with:
• Prompt Engineering
• Context Engineering (chunking, metadata enrichment, retrieval tuning)
• RAG architectures
• Experience with AWS Cloud, including:
• AWS Bedrock
• Lambda, API Gateway
• S3, DynamoDB, RDS
• ECS/Fargate or EC2
• AWS Certification (Added advantage) – e.g., AWS Certified Developer / Cloud Practitioner or above.
• Familiarity with LLM frameworks (LangChain, LlamaIndex).
• Understanding of REST APIs, microservices architecture.
• Experience with Docker and CI/CD pipelines.

What We Offer - Opportunity to work on cutting-edge GenAI products.

• Fast-paced startup/product environment.
• Ownership of end-to-end backend systems.
• Collaborative and innovation-driven culture.