GEN AI

Greetings from Tata Consulting ServicesTCS is Hiring for GEN AIExperience : 5-9 yearsLocation: Hyderabad
Please find the JD belowAbout the RoleThis is a Full Stack Software Development Engineer role within a team building customer- and workforce-facingconversational AI solutions, responsible for building next-generation conversational AI, intelligent search, andknowledge systems that power customer and associate experiences across multiple channels. This role requireshands-on expertise in designing, developing, and productionizing scalable, secure, and enterprise-grade GenAIsolutions across cloud and on-premise environments.Key Responsibilities● Design and develop LLM-powered applications for conversational AI, knowledge retrieval, and insights delivery● Build and orchestrate end-to-end GenAI pipelines, including prompt engineering, RAG, and agent-based workflows● Develop and manage LLM agents (tool usage, API integration, function calling)●Integrate LLMs across cloud and on-prem/open-source environments● Build RAG data pipelines (chunking, indexing, metadata enrichment)●Implement evaluation frameworks covering accuracy, hallucination, latency, safety, and validation (LLM-as-judge,human-in-loop)● Apply AI safety and guardrails, including prompt injection prevention and response validation● Optimize models using prompt tuning, embeddings, and fine-tuning techniques● Develop multimodal conversational experiences (text and voice)● Build scalable backend services using microservices and REST APIs● Enable observability (latency, token usage, cost, drift, quality monitoring)● Contribute to POCs, experimentation, and adoption of emerging GenAI technologiesRequired SkillsCore Engineering● Strong proficiency in Java / J2EE, Spring Boot, RESTful APIs● Strong proficiency in Python for AI/ML and GenAI workflows● Experience in building distributed systems and microservices architecturesGenAI & LLM Expertise● Hands-on experience with LLM frameworks (LangChain, LangGraph, Semantic Kernel) and RAG-basedknowledge retrieval systems● Strong understanding of prompt engineering, workflow orchestration, and agent-based systems (tool usage,function calling)● Experience with vector databases, embeddings, and semantic search● Experience working with LLMs across cloud platforms and on-prem/open-source models● Experience designing LLM evaluation pipelines (benchmarking, prompt testing, LLM-as-judge)● Strong understanding of hallucination mitigation, AI safety, guardrails, and prompt injection prevention● Knowledge of PII handling and governance/compliance framework

Work arrangement
No