Job Description – AI / LLM Engineer
- *Company:** Kybrix Technologies Pvt Ltd
- *Position:** AI / LLM Engineer
- *Experience:** 1\+ Years
- *Employment Type:** Full\-Time
- *Location:** Mohali, Punjab (On\-site)
About the Role
Kybrix Technologies is seeking an AI / LLM Engineer passionate about Generative AI, Agentic AI, Large Language Models (LLMs), and AI Automation.
The ideal candidate should have hands\-on experience working with open\-source LLMs such as Llama, Qwen, DeepSeek, Mistral, and GPT\-based systems. You will be responsible for deploying, configuring, fine\-tuning, and orchestrating AI agents capable of performing complex business tasks autonomously.
You will work on cutting\-edge AI platforms involving multi\-agent systems, autonomous workflows, OCR\-based document intelligence, Retrieval\-Augmented Generation (RAG), and enterprise AI solutions.
Key ResponsibilitiesLLM Engineering
- Install, configure, and deploy open\-source LLMs.
- Work with models such as:
- Llama
- Qwen
- DeepSeek
- Mistral
- Gemma
- GPT\-based models
- Fine\-tune and optimize models for business\-specific use cases.
- Perform prompt engineering and model evaluation.
- Optimize inference performance using:
- vLLM
- Ollama
- Hugging Face TGI
- TensorRT\-LLM
Agentic AI Development
- Design and build AI agents capable of autonomous task execution.
- Develop planning agents and reasoning workflows.
- Build multi\-agent systems using:
- LangGraph
- CrewAI
- OpenAI Agents SDK
- AutoGen
- LangChain
RAG \& Knowledge Systems
- Build Retrieval\-Augmented Generation (RAG) solutions.
- Implement document ingestion pipelines.
- Develop semantic search systems.
- Work with vector databases including:
- Qdrant
- Pinecone
- Weaviate
- ChromaDB
OCR \& Document Intelligence
- Build intelligent document processing systems.
- Extract information from:
- PDFs
- Invoices
- KYC documents
- Contracts
- Forms
- Integrate OCR systems with AI workflows.
- Work with:
- Tesseract OCR
- EasyOCR
- Google Vision AI
- Azure Document Intelligence
AI Infrastructure
* Deploy AI workloads on
- Kubernetes
- Docker
- Linux Servers
- GPU Infrastructure
- Configure model serving environments.
- Monitor performance, latency, and GPU utilization.
Development \& Integration
- Build REST APIs and backend services.
- Integrate AI services with web applications.
- Develop scalable microservices for AI workflows.
- Collaborate with product and engineering teams.
Required SkillsProgramming
AI/ML Frameworks
- PyTorch
- TensorFlow
- Hugging Face Transformers
- PEFT
- LoRA
- QLoRA
LLM Technologies
- Llama
- Qwen
- DeepSeek
- Mistral
- OpenAI APIs
- Anthropic APIs
Agent Frameworks
- LangChain
- LangGraph
- CrewAI
- AutoGen
- OpenAI Agents SDK
Vector Databases
- Qdrant
- Pinecone
- Weaviate
- ChromaDB
Cloud \& DevOps
- Docker
- Kubernetes
- Linux
- AWS
- Azure
- GCP
Databases
Preferred Qualifications
- Experience deploying models on GPU servers.
- Experience building AI agents from scratch.
- Knowledge of MCP (Model Context Protocol).
- Understanding of distributed AI systems.
- Experience with RAG and vector search architectures.
- Familiarity with AI observability and monitoring tools.
Nice to Have
- Experience with OpenClaw.
- Experience with AI marketplaces and agent platforms.
- Knowledge of MLOps practices.
- Knowledge of CI/CD pipelines for AI systems.
- Experience working with Kubernetes\-based AI deployments.
What You'll Work On
- AI Agent Marketplace Platform
- Autonomous Coding Agents
- Testing Agents
- Planning Agents
- OCR\-based Document Intelligence Systems
- Enterprise AI Automation Solutions
- Multi\-Agent Orchestration Platforms
- AI\-Powered Business Applications
Pay: ₹15,000\.00 \- ₹30,000\.00 per month
Benefits
Work Location: In person