Role & responsibilities

We are looking for a Senior AI Engineer to design and build an intelligent, proactive device-health monitoring and automated customer support ecosystem. In this role, you won't just build standalone modelsyou will architect an end-to-end system that automatically detects and classifies hardware/software issues from massive streams of device telemetry, and empowers an autonomous AI Agent to diagnose and guide customers through real-time troubleshooting via our chatbot.

You will bridge the gap between heavy big-data analytics (BigQuery) and cutting-edge GenAI (Agentic workflows, RAG, and SLM fine-tuning).

Key Responsibilities

1. Agentic AI & Conversational Experience

- Design and implement autonomous, multi-agent workflows using frameworks like LangChain, LangGraph, CrewAI, or AutoGen.
- Equip the customer-facing chatbot with secure "tools" (function calling) to fetch real-time device health metrics, look up subscription details, and trigger diagnostic workflows.
- Build advanced RAG (Retrieval-Augmented Generation) systems using text from historical support tickets, engineering documentation, and product manuals to provide hyper-accurate customer guidance.

2. Device Diagnostics & Anomaly Detection

- Develop traditional machine learning and time-series models to process raw device health data and predict failures before they happen.
- Build automated multi-class classification models to categorize root-cause failure modes (e.g., connectivity vs. hardware degradation) based on telemetry logs.
- Leverage BigQuery ML (BQML) and advanced SQL to optimize analytical processing directly inside our data lake.

3.



Model Optimization & Fine-Tuning

- Fine-tune open-source LLMs/SLMs (e.g., Llama 3, Mistral, Phi-3) on proprietary support tickets and diagnostic logs to build deep, domain-specific troubleshooting intelligence.
- Apply model compression and quantization techniques (GGUF, AWQ) to optimize model performance, token costs, and inference latency.

4. MLOps & Architecture

- Build scalable middleware APIs (Python/FastAPI) to orchestrate interactions between the frontend chatbot, the AI agent layer, and our BigQuery data lake.
- Establish robust evaluation and monitoring frameworks (e.g., LangSmith, Phoenix, or TruLens) to track agent behavior, prevent hallucinations, and ensure guardrails.

Preferred candidate profile

Technical Requirements

- AI/GenAI: Deep understanding of Transformer architectures, prompt engineering, semantic search, vector databases (e.g., Pinecone, Milvus, or BigQuery Vector Search), and LLM fine-tuning.
- Data Stack: Exceptional SQL skills and hands-on experience working with massive datasets in Google BigQuery (or Snowflake/Databricks equivalents).
- Programming: Expert-level Python and familiarity with classical ML libraries (scikit-learn, PyTorch/TensorFlow).
- Architecture: Robust understanding of RESTful APIs, microservices, and asynchronous event-driven patterns.

Preferred Qualifications

- Prior experience in the Consumer IoT, Smart Home, Telecom, or Connected Hardware space is a massive plus.
- Experience deploying Small Language Models (SLMs) on resource-constrained environments or optimized edge cloud runtimes.
- Familiarity with data security, compliance protocols, and handling user-device logs.

📌 Senior / Lead AI Engineer (IoT & Agentic Systems) (Noida)
🏢 Plakxa Business Consulting
📍 Noida