About the Role :

We are looking for an experienced Python Generative AI Developer / Agentic AI Engineer / AI Architect with strong expertise in Python, Agentic AI, AWS, FastAPI, and Retrieval-Augmented Generation (RAG). The ideal candidate will be responsible for designing, developing, and deploying scalable AI-powered applications and intelligent agent-based solutions using modern generative AI technologies and cloud-native architectures.

Key Responsibilities :

- Design, develop, and deploy Generative AI applications using Python and modern AI frameworks.

- Build Agentic AI solutions capable of planning, reasoning, tool usage, and executing multi-step workflows.

- Develop and integrate AI agents with enterprise applications, APIs, databases, and external tools.

- Design and implement Retrieval-Augmented Generation (RAG) pipelines for context-aware and knowledge-driven AI applications.

- Develop scalable backend services and RESTful APIs using FastAPI.

- Build, deploy, and manage AI applications on AWS cloud services.

- Integrate Large Language Models (LLMs) with enterprise data sources and business workflows.

- Implement prompt engineering, context management, and response optimization techniques.

- Develop document ingestion, chunking, embedding, retrieval, and vector search pipelines.

- Design secure, scalable, and production-ready AI architectures.

- Optimize AI application performance, latency, scalability, and cost.

- Implement logging, monitoring, evaluation, and error-handling mechanisms for AI systems.

- Collaborate with data scientists, software engineers, architects, and business stakeholders to translate business requirements into AI-driven solutions.

- Follow best practices for application security, responsible AI, testing, and deployment.

Required Skills and Qualifications:

- 6 - 12 years of relevant professional experience in software development, AI engineering, or solution architecture.

- Strong programming expertise in Python.

- Hands-on experience in Generative AI and Large Language Models (LLMs).

- Practical experience designing and implementing Agentic AI applications and workflows.

- Strong experience with AWS cloud services for deploying and managing AI applications.

- Hands-on experience building APIs and backend services using FastAPI.

- Strong understanding of Retrieval-Augmented Generation (RAG) architecture and implementation.

- Experience integrating LLMs with enterprise systems, APIs, and external data sources.

- Knowledge of embeddings, vector databases, semantic search, and information retrieval.

- Understanding of prompt engineering, LLM orchestration, and AI application development.

- Experience with REST APIs, application integration, testing, and deployment.

- Strong analytical, problem-solving, and communication skills.

Preferred Skills:

- Experience with AI agent frameworks such as LangChain, LangGraph, or AutoGen.

- Familiarity with Amazon Bedrock and AWS AI/ML services.

- Experience with vector databases such as FAISS, Pinecone, Weaviate, or Chroma.

- Knowledge of Docker, Kubernetes, CI/CD, and cloud-native deployment practices.

- Experience implementing LLM evaluation, guardrails, observability, and security controls.

- Familiarity with MLOps or LLMOps practices for deploying and maintaining AI solutions.

- Experience designing enterprise-grade AI architectures and scalable distributed systems.