Generative AI Engineer

Tata Consultancy Services; Hyderabad; On-site; INR 1,200,000 - 1,800,000; Full time

Job summary

Tata Consultancy Services in Hyderabad, India invites a skilled backend engineer to build and productionize cloud-native services and AI/LLM pipelines. You will design Python-based APIs (FastAPI) and resilient microservices, and implement embeddings, RAG, and model versioning for scalable inference.

Responsibilities include packaging, serving, and monitoring models for real-time and batch workloads, plus hands-on Kubernetes debugging with Helm deployments.

Responsibilities

• Build and Productionize cloud native backend services and AI/LLM inference pipelines.
• Design and develop Python-based APIs and microservices (FastAPI, async patterns) and agentic AI workflows using LangChain/LangGraph.
• Implement and optimize LLM capabilities including embeddings, RAG, vector search, prompt/context engineering, and model versioning.
• Package, serve, and monitor models for real-time and batch inference, ensuring operational readiness and performance.
• Build event driven, resilient integrations and containerized services, with hands-on Kubernetes debugging and Helm-based deployments.
• Apply strong systems design principles (concurrency, caching, reliability, rate limiting) and robust data engineering practices.
• Cloud exposure preferred (Azure/AKS, managed services), with bonus experience in performance tuning, frontend collaboration, and model governance/monitoring.

Skills

Python

FastAPI

Microservices

Kubernetes

Helm

LangChain

LangGraph

Azure AKS

Embeddings

RAG

Tools

Docker

Helm

LangChain

LangGraph

AKS

Job description

• Build and Productionize cloud native backend services and AI/LLM inference pipelines.
• Design and develop Python-based APIs and microservices (FastAPI, async patterns) and agentic AI workflows using LangChain/LangGraph.
• Implement and optimize LLM capabilities including embeddings, RAG, vector search, prompt/context engineering, and model versioning.
• Package, serve, and monitor models for real-time and batch inference, ensuring operational readiness and performance.
• Build event driven, resilient integrations and containerized services, with hands-on Kubernetes debugging and Helm-based deployments.
• Apply strong systems design principles (concurrency, caching, reliability, rate limiting) and robust data engineering practices.
• Cloud exposure preferred (Azure/AKS, managed services), with bonus experience in performance tuning, frontend collaboration, and model governance/monitoring.