Job Description
We are seeking a highly skilled Backend Engineer (AI + Python/FastAPI) to design, build, and optimize cutting-edge AI-driven systems. You will work on advanced Agentic AI, RAG pipelines, LLM integrations, and serverless microservices while collaborating closely with cross-functional teams. This role is ideal for someone who enjoys solving complex technical problems, architecting scalable backend systems, and pushing the boundaries of AI engineering.
Responsibilities:
- •Develop and maintain backend services using Python and FastAPI.
- •Build and optimize AI-driven pipelines using LangChain, Generative AI, and Agentic AI patterns.
- •Implement and manage vector embeddings, chunking logic, and vector search using Pinecone or Qdrant.
- •Architect scalable RAG (Retrieval-Augmented Generation) systems and hybrid search mechanisms.
- •Integrate and manage LLM APIs such as OpenAI, Anthropic, and others.
- •Develop autonomous agents and multi-step agentic workflows.
- •Build caching layers with Redis to ensure low-latency performance.
- •Design, develop, and optimize serverless architectures using AWS Lambda, versions, aliases, and Step Functions.
- •Set up monitoring, logging, and event tracking using AWS CloudWatch.
- •Manage relational and NoSQL databases including PostgreSQL, MySQL, and Firestore.
- •Build and maintain containerized deployments using Docker.
- •Develop and maintain CI/CD pipelines using GitHub Actions.
- •Work with BM25, ElasticSearch, and hybrid retrieval methods.
- •Apply prompt engineering practices and evaluate LLM output quality.
- •Participate in Agile/Scrum ceremonies using tools like Jira or Nifty.
- •Collaborate with cross-functional teams and take part in architectural decision-making.
Requirements:
- •Strong proficiency in Python and backend development.
- •Hands-on experience with FastAPI for building scalable APIs.
- •Practical experience with LangChain, LLMs, and Agentic AI workflows.
- •Proficiency with vector databases such as Pinecone or Qdrant.
- •Hands-on experience with embeddings, similarity search, and RAG pipelines.
- •Strong understanding of Redis caching and optimization strategies.
- •Proven experience with Docker and containerized development.
- •Strong grasp of serverless architectures and microservice design.
- •Experience with AWS Lambda, versioning, aliases, and Step Functions.
- •Familiarity with CloudWatch monitoring and logging.
- •Solid database experience with PostgreSQL, MySQL, or Firestore.
- •Strong Git/GitHub knowledge for collaboration.
- •Experience building CI/CD pipelines (preferably GitHub Actions).
- •Practical experience integrating and using OpenAI, Anthropic, or similar LLM APIs.
- •Understanding of search/retrieval systems such as BM25, ElasticSearch, and hybrid methods.
- •Strong grounding in prompt engineering techniques and evaluation.
- •Experience working in Agile/Scrum environments.