ML & Search Engineer

Archzos; India; On-site; INR 1,800,000 - 3,000,000; Full time

Job summary

Archzos in India is seeking an ML / Search Engineer to build the intelligence layer powering archzOS, including vector search, graph traversal, and hybrid retrieval, with a goal of low-latency P99 at scale.

You will design and optimize retrieval architectures, implement ranking models, and collaborate with product teams to translate user needs into search quality improvements. Strong ML, IR/NLP expertise, and experience with vector databases are essential.

Qualifications

• Strong ML background with hands-on information retrieval or NLP experience.
• Experience with vector databases (Pinecone, Weaviate, or similar).
• Proficiency in Python with PyTorch or JAX.
• Understanding of graph databases and traversal algorithms.
• Comfort with distributed systems and high-throughput data pipelines.

Responsibilities

• Design and implement hybrid retrieval systems (vector + graph) at production scale.
• Build and tune ranking models for organizational search.
• Optimize indexing pipelines for 50+ integration sources.
• Research and evaluate new retrieval architectures.
• Collaborate with product to translate user needs into search quality improvements.

Skills

ML & IR/NLP

Vector retrieval

Python (PyTorch/JAX)

Graph databases & traversal

Distributed systems

Tools

Vector databases (Pinecone/Weaviate)

Job description

ML / Search Engineer

You'll build the intelligence layer that makes archzOS actually work — vector search, graph traversal, hybrid retrieval, and the ranking models that make 42ms P99 possible at scale. This is a hard technical problem and we want people who find it interesting.

Responsibilities

• Design and implement hybrid retrieval systems (vector + graph) at production scale
• Build and tune ranking models for organizational search
• Optimize indexing pipelines for 50+ integration sources
• Research and evaluate new retrieval architectures
• Collaborate with product to translate user needs into search quality improvements

Requirements

• Strong ML background with hands-on experience in information retrieval or NLP
• Experience with vector databases (Pinecone, Weaviate, or similar)
• Python proficiency with PyTorch or JAX
• Understanding of graph databases and traversal algorithms
• Comfort with distributed systems and high-throughput data pipelines

Nice to have

• Research background or publications in information retrieval
• Experience with knowledge graphs or graph neural networks
• Prior work on enterprise search products
• Familiarity with transformer-based embedding models