E
EXL
AI Engineer
Senior Analyst, RAG/LLM Specialist
On-siteSeniorAI Engineerposted 1w ago
Role summaryAI-generated
This role focuses on developing and maintaining Retrieval-Augmented Generation (RAG) pipelines, including PDF parsing, text chunking, and embedding generation using Python and LLM APIs. The candidate will also design, test, and version‑control prompts to ensure reliable model responses within a LangChain or Autogen framework.
Skills required
About this role
Role Overview: Hands-on developer responsible for implementing prompt workflows, data
chunking, and maintaining the accuracy of AI outputs.
Responsibilities
Key Responsibilities
- Implementation: Build and test basic to intermediate RAG systems using frameworks like
- LangChain or Autogen.
- Data Processing: Write Python scripts for PDF/document parsing, text chunking, and embedding generation.
- Prompt Engineering: Systematically test and version-control system prompts to achieve reliable model responses.
Qualifications
Required Skills & Qualifications
- Tech Stack: Strong Python programming, familiarity with APIs (OpenAI, Anthropic), basic LangChain/LlamaIndex usage.
- Qualifications: Bachelor’s in CS or related field; 3–4 years software or data engineering experience with demonstrated exposure to LLM APIs.
Apply on EXL →Opens in new tab
score your resume against this role
Similar open roles
MM
NEWSenior Software Engineer - Generative AI & Digital Experience @MarshTech
On-siteSeniorAI Engineer
yesterday
J
NEW4815 - Full Stack AI Engineer, Global Information Security (Vice President)
On-siteSeniorAI Engineer
yesterday