Is there any specific skill required for this job?

The candidate should have sound communication skills and sound communication skills for this job.

Who can apply for this job?

Both Male and Female candidates can apply for this job.

Is it a work from home job?

No, it's not a work from home job and can't be done online. You can explore and apply for other work from home jobs in Bengaluru/Bangalore at apna.

Are there any charges or deposits required while applying for the role or while joining?

No work-related deposit needs to be made during your employment with the company.

How can I apply for this job?

Go to the apna app and apply for this job. Click on the apply button and call HR directly to schedule your interview.

What is the last date to apply?

The last date to apply for this job is . For more details, download apna app and find Full Time jobs in Bengaluru/Bangalore . Through apna, you can find jobs in 64 cities across India. Join NOW!

Large Language Model and Retrieval-Augmented Generation Engineer

Indium Software India

Large Language Model and Retrieval-Augmented Generation Engineer

Indium Software India

Bengaluru/Bangalore

Not disclosed

Work from Office

Full Time

Min. 5 years

Job Description

Data Scientist

Job Description – LLM / RAG Engineer

We are looking for a skilled LLM / RAG Engineer to design, build, and operate production-grade AI systems using large language models. The ideal candidate will have strong hands-on experience with RAG architectures, data preparation, evaluation, and LLMOps, along with the ability to deliver reliable and user-friendly conversational applications.

Key Responsibilities:

LLM Fundamentals

• Understand how LLMs generate text and common failure modes such as hallucinations and context limitations • Design effective prompts including system prompts, grounding techniques, and few-shot examples • Differentiate between embedding and generation models • Decide when to use RAG vs. fine-tuning

RAG Architecture (Critical)

• Design and implement semantic and structure-aware chunking strategies • Build vector and hybrid search pipelines • Implement query rewriting, top-k selection, and re-ranking • Apply metadata filtering and enable citations for grounded responses

Unstructured Data Processing

• Extract text from PDFs, DOCX, HTML, and OCR sources • Perform data cleaning, deduplication, and normalization • Prepare chunk-ready datasets with rich metadata

Structured Data & Analytics

• Strong SQL proficiency • Implement text-to-SQL workflows with guardrails • Enable schema-aware retrieval and analytical querying • Combine computed results with clear LLM-generated explanations

Evaluation & Monitoring

• Measure retrieval relevance and answer groundedness • Build offline evaluation datasets with human review • Monitor latency, cost, and response quality in production

LLMOps

• Manage prompt and model versioning • Support rollbacks and safe deployments • Track cost, performance, and system reliability

Frontend & Conversational UX

• Design conversational experiences with follow-up handling • Implement citations and confidence indicators in responses • Build lightweight frontends using Flask • Capture and utilize user feedback for continuous improvement

Required Skills

• Strong understanding of LLM and RAG systems • Experience with vector databases and retrieval pipelines • Solid SQL and data handling expertise • Hands-on experience with Flask-based applications • Strong problem-solving, communication, and system design skills