You will get Build a production search system that handles 1M to 100M documents
Project details
Build a production search system handling 1M to 100M documents with sub-100ms p95 latency. I built and operated 800M-profile vector search using Qdrant + BM25 hybrid retrieval + cross-encoder reranking, and I bring that exact playbook to your stack.
What you get:
• Architecture: vector DB choice (Qdrant, Pinecone, Weaviate, pgvector), retrieval strategy, reranking layer
• Ingestion pipeline: dedup, chunking, embedding generation, incremental sync
• Hybrid retrieval: BM25 + dense vectors fused via RRF
• Cross-encoder reranking for top-N precision
• Eval harness with a golden set so you can measure changes objectively
• Latency tuning to sub-100ms p95
• Sharding strategy at 25M+ scale
• Monitoring for query latency, recall, throughput
Tech stack flexible: Python/Node/Go on the API side, Qdrant/pgvector/Elasticsearch/Pinecone on the index side.
I deliver working code, deployment scripts, eval results, and a runbook your team can operate after handoff.
What you get:
• Architecture: vector DB choice (Qdrant, Pinecone, Weaviate, pgvector), retrieval strategy, reranking layer
• Ingestion pipeline: dedup, chunking, embedding generation, incremental sync
• Hybrid retrieval: BM25 + dense vectors fused via RRF
• Cross-encoder reranking for top-N precision
• Eval harness with a golden set so you can measure changes objectively
• Latency tuning to sub-100ms p95
• Sharding strategy at 25M+ scale
• Monitoring for query latency, recall, throughput
Tech stack flexible: Python/Node/Go on the API side, Qdrant/pgvector/Elasticsearch/Pinecone on the index side.
I deliver working code, deployment scripts, eval results, and a runbook your team can operate after handoff.
AI Algorithms
Large Language Model, Transformer ModelAI Applications
Natural Language UnderstandingAI Development Language
PythonAI Tools
Hugging FaceAI Models
BERT, GPT-4What's included
| Service Tiers |
Starter
$5,000
|
Standard
$10,000
|
Advanced
$15,000
|
|---|---|---|---|
| Delivery Time | 7 days | 14 days | 30 days |
Number of Revisions | 2 | 3 | 5 |
AI Model Integration | - | ||
Batch Normalization | - | - | - |
Database Integration | |||
Detailed Code Comments | |||
Image Upscaling | - | - | - |
MLOps | - | - | |
Model Deployment | - | - | |
Model Documentation | - | - | - |
Model Monitoring | - | - | |
Model Testing & Optimization | - | ||
Model Tuning | - | - | |
Natural Language Processing | - | - | - |
NLP Tokenization | - | - | - |
Pre-Training | - | - | - |
Prompt Engineering | - | - | - |
Setup File | |||
Source Code |
About Badal
Senior AI Engineer | AI Agents + RAG, Voice Agent, GEO/AEO
Bengaluru, India - 11:44 pm local time
I led the technical build at two AI-first startups:
▸ An AI candidate sourcing platform running 800M-profile vector search in production (Qdrant + hybrid retrieval + cross-encoder reranking, sub-100ms latency), and
▸ A GEO/AEO audit platform monitoring AI visibility of any brand across ChatGPT, Claude, Perplexity, Gemini, and Google AI Overviews.
My niche is the 20% custom AI work that off-the-shelf SaaS can't deliver. I focus on systems that actually ship to production with eval harnesses, observability, retry logic, and cost controls. Not POCs that rot in a sandbox.
Stack: Python, Claude Sonnet 4, OpenAI GPT-5, Qdrant, vLLM, n8n, FastAPI, LangChain, LangGraph, Portkey/Langfuse for observability.
What I deliver:
▸ Custom AI Agents. Multi-step Claude or OpenAI agents with proper orchestration, eval harnesses, retry logic, and observability. LangChain, LangGraph, or custom Python. Production-ready in 3-4 weeks.
▸ Production RAG Systems. Hybrid retrieval (dense + sparse + RRF fusion + cross-encoder reranking) with eval harness across your real corpus. Stack flexibility on vector DB (Qdrant, Pinecone, Weaviate, pgvector) and LLM (Claude, OpenAI, Gemini).
▸ Custom Support Chatbots. RAG over your docs AND ticket history. The systems Intercom Fin, Ada, and Zendesk AI can't deliver because they need deeper integration. Includes deflection-rate eval before launch.
▸ GEO / AEO Audit + Implementation. Get your brand cited when buyers ask ChatGPT, Claude, Perplexity, Gemini, or Google AI Overview about your category. 10-dimension audit, schema markup, llms.txt setup, citation strategy. Monthly retainer option for ongoing visibility tracking.
▸ n8n / Make Workflow Automation. The engineering-depth tier with custom Claude or OpenAI nodes, retry logic, observability, and Python sub-workflows. For projects that outgrew drag-and-drop.
▸ Cold Outreach + Lead-Gen Pipelines. Apollo + Instantly + Smartlead + Claude personalization. Account research agents that take a company URL and output decision-makers + intent signals + outreach angle. Built scraping infrastructure handling 5M+ records/day with anti-bot circumvention.
▸ Custom Sourcing Agents for Recruiting Firms. Multi-source candidate search beyond LinkedIn and Indeed, with custom scoring matched to your hiring criteria. For boutique recruiting firms with real engineering budget.
How I work:
1. 30-min discovery call to find the actual bottleneck. Most prospects describe the symptom, not the root cause.
2. Fixed-scope quote with one round of revision included. You know the price before we start.
3. Weekly Loom updates plus Slack or Notion for ongoing work.
4. Ship to production with eval harness, observability, and 30 days of post-launch bug-fix support.
Steps for completing your project
After purchasing the project, send requirements so Badal can start the project.
Delivery time starts when Badal receives requirements from you.
Badal works on your project following the steps below.
Revisions may occur after the delivery date.
Discovery and architecture doc
30-min call to scope your data, query patterns, and latency targets. Deliver architecture doc within 3 days covering tech choices, ingestion pipeline, retrieval strategy, eval plan, and milestones.