AI Engineer • Machine Learning Engineer
$
AI & ML Engineer with 2+ years of industrial experience building production-grade autonomous systems, local LLM architectures, and advanced ML models. Successfully shipped 24+ enterprise AI modules.
Enterprise AI modules
Shipped across production tenants
Production case studies
End-to-end AI/ML systems, documented
Years industrial experience
Building autonomous AI systems
Peak model accuracy
Fine-tuned classification (OmniShield)
A selection of end-to-end AI/ML systems I've designed, built, and operated — from autonomous agents to high-throughput inference.
Mail-server gateway (Postfix Milter) that intercepts every inbound message, runs a fine-tuned BERT core (M-BSCE) through an asynchronous inference pipeline (RabbitMQ + Celery), and adds multimodal threat detection (PaddleOCR for Quishing) with SOAP clawbacks to the upstream mail system.
Autonomous multi-channel AI platform that unifies chat, voice, and email behind microservices and an API gateway, with shared context across channels.
Telecom recommendation agent fine-tuned on Qwen2.5-3B with LoRA, quantized to GGUF via Unsloth for cheap, low-latency inference.
Production-grade across the AI stack — agentic orchestration, grounded retrieval, local inference, and deployment.
Production APIs, relational engines, and graph stores powering AI services.
Grounded RAG systems over vector and graph indexes with semantic + hybrid search.
Multi-agent systems, function calling, and human-in-the-loop orchestration frameworks.
LLM adaptation (PEFT, quantization) and real-time voice / TTS / STT pipelines.
Local GPU inference with KV-cache + runtime buffer pre-allocation, plus API routing.
Detection, recognition, and document extraction across print and handwriting.
Container orchestration, CI/CD, experiment tracking, and Linux production runtime.
Industrial experience building autonomous systems, LLM infrastructure, and ML models that run in production.
Recognized for shipping production-grade AI systems and for cost-eliminating LLM deployment work at Business Automation Ltd.
Aggregated 4 years of total experience (study + engineering journey starting in 2022) with over 1.5+ years of dedicated professional industrial experience, strictly focusing on end-to-end autonomous agent architectures over standard LLM API implementations.
Statistical modeling and exploratory data analysis for product-facing ML systems. Trained deep learning networks with PyTorch and TensorFlow for downstream GenAI fine-tuning work.
Live view of the OpenClaw multi-channel orchestration pipeline — hover a stage to trace its data path.
Single entry point that authenticates and routes per-channel traffic.
Per-channel microservices normalize chat, voice, and email into a common event stream.
Cross-channel session store and vector memory keep state consistent across surfaces.
Central agent that dispatches tasks across services and channels with shared context.
Query → Entities → Community Summaries → Answer
Agents, RAG pipelines, local LLM inference — if it needs to run in production, I want to hear about it.
sourav.rskh.sr@gmail.com