Senior RAG & Retrieval Engineer

Whizzbridge; Lahore; On-site; PKR 1,800,000 - 3,200,000; Full time

Benefits offered by this job

Medical Insurance

Paid Udemy Courses and Certifications

Job summary

Whizzbridge is hiring a Mid to Senior RAG and Retrieval Engineer in Lahore to design, build, and tune retrieval augmented generation systems grounded in client data. The role covers end-to-end retrieval pipelines, embedding model selection, and hybrid search strategies across structured and unstructured corpora.

You will optimize recall, grounding quality, and latency, while reducing hallucinations and coordinating with client SMEs for domain accuracy.

Qualifications

• Bachelor's degree in Computer Science or related field or equivalent experience.
• 3+ years of professional engineering experience with hands-on RAG work.
• Strong Python programming skills and production experience.

Responsibilities

• Design, build and tune retrieval augmented generation systems grounded in client data.
• Own full retrieval pipeline: ingestion, parsing, embedding, indexing, retrieval, reranking.
• Evaluate embedding models against client corpora; design chunking strategies.
• Implement hybrid search and reranking; optimize cost and latency at scale.
• Create retrieval evaluation suites with recall, context accuracy and relevance metrics.
• Reduce hallucination; plan embeddings migrations and full corpus re-indexing.
• Collaborate with client SMEs to define correct answers in their domain.

Skills

Python

Production RAG

Vector DBs

Embedding models

Hybrid search

Reranking

Retrieval orchestration

Evaluation with metrics

English proficiency

Education

Bachelor's degree in CS/Software Eng

Tools

pgvector

Pinecone

Qdrant

Weaviate

Chroma

LlamaIndex

LangChain

LangGraph

DSPy

Job description

Whizzbridge is hiring a Mid to Senior RAG and Retrieval Engineer in Lahore to design, build, and tune retrieval augmented generation systems grounded in client data. The role covers end-to-end retrieval pipelines, embedding model selection, and hybrid search strategies across structured and unstructured corpora.

You will optimize recall, grounding quality, and latency, while reducing hallucinations and coordinating with client SMEs for domain accuracy.