GenAI: Job Description & Summary: Job Position Title: IN_Senior Associate_Gen AI developer _Emerging Business_Advisory_Bangalore (India) Responsibilities: • Solution Development: Develop and deploy enterprise-grade Generative AI applications, APIs, and microservices. • LLM Orchestration & RAG: Optimize Retrieval-Augmented Generation (RAG) pipelines and advanced search architectures to ground LLMs on proprietary enterprise data. • Agentic AI: Build multi-agent systems and autonomous workflows using orchestration frameworks to automate complex, multi-step business processes. • Model Integration: Integrate leading commercial and foundational models via enterprise cloud environments (Azure OpenAI, AWS Bedrock, or GCP Vertex AI / Model Garden). • Responsible AI & Guardrails: Implement safety guidelines, content moderation, data privacy controls, and guardrails to ensure compliant and ethical AI deployments. Establish evaluation frameworks to measure LLM performance (latency, accuracy, bias, drift, and cost) and set up monitoring in production. • Client Collaboration & PoCs: Rapidly prototype Proof of Concepts (PoCs) to showcase GenAI capabilities to internal leaders and external clients.

Mandatory skill sets: • 3–6 years of experience in software development with strong computer science fundamentals. • Expert Python Programming: Deep proficiency in Python and its standard libraries. • API Development: Experience building robust and secure RESTful/GraphQL APIs using frameworks like FastAPI, Flask, or Django. • Cloud Ecosystems (Any One Preferred): Hands-on experience with at least one major cloud platform’s AI ecosystem: • GCP: Vertex AI, Vertex AI Search and Conversation, Vertex AI Model Garden, Gemini API, Google ADK. • Microsoft Azure: Azure OpenAI Service, Azure AI Search, Azure Databricks, AI Foundry • AWS: Amazon Bedrock, Amazon SageMaker. • Databases: Proficiency in SQL and NoSQL databases. • Frameworks: Extensive experience with LangChain, LlamaIndex or LangGraph. • Vector Databases & Search: Practical experience with vector databases/search engines such as Pinecone, Milvus, Qdrant, Chroma, Vertex AI Vector Search, or Azure AI Search. • Prompt Engineering: Proven ability in designing complex system prompts, few-shot learning, and chain-of-thought prompting. • Embeddings: Deep understanding of text embeddings, semantic search, and advanced chunking strategies. 3. DevOps & LLMOps · Containerization using Docker and basic understanding of Kubernetes (e.g., GKE, AKS, or EKS). · Experience with Git-based CI/CD pipelines. · Familiarity with LLM monitoring tools (e.g., LangSmith, Langfuse or Arize Phoenix).

Preferred skill sets: · Experience in Fine-tuning models (PEFT, LoRA) using Hugging Face libraries. · Knowledge of Graph databases (e.g., Neo4j) for GraphRAG implementations. · Familiarity with UI prototyping frameworks like Streamlit, Chainlit, or Gradio. · An understanding of MLOps pipelines on GCP (Vertex AI Pipelines), Azure, or AWS.

Years of experience required: 4- 7 years

Education qualification: BE/ Btech/ Mtech/ MCA/ MBA (fulltime)