Description :

About the Role :

We are looking for a highly skilled Backend Engineer with strong expertise in Python, FastAPI, and AWS cloud services. The ideal candidate will have practical experience building GenAI-powered applications, implementing RAG pipelines, and integrating LLMs into production-grade systems. You will work closely with cross-functional teams to design, develop, and deploy scalable backend services and AI-driven solutions.

Key Responsibilities :

- Design, develop, and maintain scalable backend services using Python and FastAPI.

- Implement robust software architectures using OOP principles and well-established design patterns.

- Build and deploy cloud-native applications using AWS services (Lambda, API Gateway, ECS, S3, CloudWatch, etc.).

- Integrate backend systems with multiple AWS services via AWS SDK.

- Work on GenAI POCs and production deployments (minimum 2 hands-on implementations).

- Design and implement RAG (Retrieval-Augmented Generation) workflowssemantic search, embeddings, vector stores (FAISS, Pinecone, Chroma), and LangChain pipelines.

- Integrate LLMs into enterprise-grade applications with focus on reliability, scalability, and performance.

- Collaborate with product, ML, and DevOps teams to deliver high-quality AI-backed solutions.

- Troubleshoot and optimize backend performance, cloud resource usage, and system reliability.

Required Skills & Qualifications :

- Strong programming expertise in Python.

- Excellent understanding of OOP concepts and design patterns.

- Proven experience with FastAPI and asynchronous programming.

- Hands-on AWS experience : Lambda, API Gateway, ECS, S3, CloudWatch, IAM, etc.

- Experience integrating and managing AWS services using AWS SDK (Boto3).

- At least 2 GenAI POCs or practical hands-on experience in real-world scenarios.

- RAG experience : semantic search, embeddings, vector databases (FAISS, Pinecone, Chroma, etc.), LangChain.

- Experience deploying and integrating LLMs in production systems.

- Total experience : 5- 8 years (L3 level).

Good-to-Have Skills :

- Experience with CI/CD pipelines (GitHub Actions, GitLab CI, Jenkins).

- Exposure to MLOps : model serving, monitoring, feature stores, inference optimization.

- Understanding of data engineering fundamentals, ETL workflows, data pipelines.

- Knowledge of cloud architecture, distributed systems, and performance optimization.

Why Join Us :

- Work on cutting-edge GenAI and cloud-native products.

- Opportunity to design and build end-to-end production-level AI systems.

- Collaborative environment with growth and learning opportunities.