Role & responsibilities

- Design and build modular AI solutions using Lang Chain, Semantic Kernel, or custom pipelines
- Develop APIs and AI agents for enterprise use cases
- Translate business requirements into scalable AI solutions
- Build ingestion pipelines and integrate enterprise data sources
- Implement embedding, reranking, and retrieval strategies for RAG pipelines
- Enforce structured outputs using Pydantic, function calling, or similar techniques
- Containerize and deploy solutions using Docker and CI/CD pipelines
- Monitor performance metrics and continuously improve system quality

Preferred candidate profile

- Solid Python skills with experience in AI frameworks (LangChain, Transformers, OpenAI SDK, LLaMA APIs)
- Hands-on experience with RAG pipelines, embeddings,



and prompt design
- Familiarity with Knowledge Graphs (Apache Jena, SPARQL)
- Experience with Vector Databases (Pinecone, Chroma, etc.)
- Knowledge of embedding models (OpenAI Ada, Cohere, BGE/E5) and reranking techniques
- Experience building microservices (FastAPI, Flask)
- Exposure to multi-agent frameworks (LangGraph, CrewAI, AutoGen)
- Understanding of Model Context Protocol (MCP)
- Cloud experience with Azure (AKS, App Service, ACI) and DevOps tools
- Integration experience with enterprise platforms (Outlook, Teams, Salesforce)

📌 Data Developer (Hyderabad)
🏢 PwC
📍 Hyderabad