Job Description

Job Title - Data Engineering Consultant - RAG, LLM & AI Agents | S&C

Management Level: 09 - Consultant

Location: PAN India

Must Have Skills: Retrieval-Augmented Generation (RAG), Large Language Models (LLM), AI Agent Development, Python, LangChain, Vector Databases (Pinecone/Weaviate/ChromaDB), Prompt Engineering

Good to Have Skills: LlamaIndex, FastAPI, Vertex AI / AWS Bedrock / Azure OpenAI, HuggingFace, Embedding Models, Docker / Kubernetes, MLflow

Job Summary:

As a Data Engineering Consultant specializing in RAG, LLMs, and AI Agent development, you will be responsible for designing and building intelligent, context-aware AI applications that leverage retrieval-augmented generation architectures and autonomous agent frameworks. Your typical day will involve developing RAG pipelines, fine-tuning and integrating LLMs, building multi-step AI agents using LangChain, and deploying these solutions in scalable production environments. You will work closely with data engineers, ML engineers, and product teams to deliver AI-powered products that create measurable business value.

Roles & Responsibilities:

Design and implement end-to-end RAG pipelines, including document ingestion, chunking, embedding, vector storage, and retrieval.
Integrate and orchestrate large language models (e.g., Gemini, GPT-4, Claude, Llama) for enterprise use cases.
Build multi-step, tool-using AI agents using frameworks such as LangChain, LlamaIndex, or custom agent loops.
Develop and optimize prompt engineering strategies for accuracy, reliability, and latency.
Select and configure vector databases (e.g., Pinecone, Weaviate, ChromaDB) for semantic search and retrieval.
Implement evaluation frameworks to assess RAG and agent output quality (relevance, faithfulness, hallucination rate).
Deploy LLM-based solutions as APIs or microservices, ensuring scalability and observability.
Collaborate with clients to identify AI use cases and translate requirements into production-ready agent architectures.

Professional & Technical Skills:

Must Have Skills: Proficiency in RAG architecture design, LLM integration, AI agent development, vector databases and prompt engineering
Hands-on experience with orchestration frameworks such as LangChain or LlamaIndex.
Strong Python skills for building and deploying LLM pipelines and agent workflows.
Experience with vector databases and embedding models for semantic retrieval.
Strong grasp of prompt engineering - few-shot learning, and chain-of-thought techniques.
Knowledge of LLM evaluation metrics and tools (e.g., RAGAS, TruLens, or custom eval pipelines).
Experience deploying AI services on cloud platforms (GCP Vertex AI, AWS Bedrock, or Azure OpenAI) is an advantage.

Additional Information:

The ideal candidate will have a passion for applied AI and a track record of delivering LLM-powered solutions in production environments.
This position is based at PAN India offices.

About Our Company | Accenture