Contribute in coding and implementation of GenAI-powered applications.
Translate functional requirements into efficient Python services.
Work with LLM orchestration frameworks (LangChain 1.0, LangGraph, OpenAI tools, custom agents).
Participate in PoCs and exploratory work for new GenAI capabilities.
Python Cloud
Build and enhance RAG pipelines using embeddings, vector databases, and chunking strategies.
Implement basic Agentic workflows under guidance from senior team members. (wherever applicable)
Work with vector search systems (PGVector, FAISS, etc.).
Implement indexing, metadata tagging, and retrieval optimizations.
Exposure to MCP / tool-integration frameworks is an added advantage.
Softskills
Participate in code reviews, design discussions, and documentation.
Follow best practices in coding standards, testing and DevOps
Collaborate with team.
Required Skills
hands-on proficiency in Python (Flask, REST, async programming).
Practical experience with Generative AI and LLM-based applications. (6 to 12 months)
Good understanding of RAG system, embeddings, vector databases.
Usage of Bedrock models through AWS
Exposure to Agentic frameworks (LangChain 1.0, LangGraph, ReAct, OpenAI Assistants, or custom agents).
Familiarity with AWS/Azure/GCP Cloud (ECS, S3, API Gateway, IAM, Bedrock).
Experience with API development, microservices, containerization, CDK etc.
Handson Knowledge Docker, GitHub Actions and policies.
Mandatory Competencies
Location: Noida, UP, India
Job Classification
Industry: IT Services & ConsultingFunctional Area / Department: Engineering - Software & QARole Category: Software DevelopmentRole: Data Platform EngineerEmployement Type: Full time