Responsibilities
- Design and develop AI-powered features for web and mobile applications.
- Build custom AI assistants using company project data.
- Implement Retrieval-Augmented Generation (RAG) pipelines.
- Fine-tune or customize open-source LLMs when required.
- Create document ingestion pipelines for PDFs, Word documents, websites, databases, APIs, and project files.
- Develop AI systems capable of answering questions based on project documentation.
- Implement semantic search using vector databases.
- Build chatbots and AI copilots for different company products.
- Integrate AI services into existing Laravel, Node.js, React, and mobile applications.
- Optimize prompts and AI responses for accuracy.
- Evaluate and improve AI model performance.
- Ensure AI security, privacy, and scalability.
- Keep up to date with the latest AI technologies.
Required SkillsProgramming
- Python (Expert)
- FastAPI or Flask
- REST APIs
- Git
AI/LLM
- OpenAI GPT
- Claude
- Gemini
- Llama
- Mistral
- DeepSeek
- Prompt Engineering
- Fine-tuning
- Function Calling
- Structured Output
RAG
- Retrieval-Augmented Generation
- Embeddings
- Chunking
- Semantic Search
- Context Management
Vector Databases
Experience with one or more:
- Pinecone
- Weaviate
- Qdrant
- ChromaDB
- Milvus
- pgvector
AI Frameworks
- LangChain
- LlamaIndex
- DSPy (preferred)
- Haystack
Databases
Cloud
- AWS
- Docker
- Kubernetes (optional)
Preferred Experience
- AI chatbot development
- Enterprise knowledge base systems
- AI document search
- OCR
- Speech-to-Text
- Text-to-Speech
- AI Agents
- Multi-Agent Systems
- MCP (Model Context Protocol)
- Agentic AI
- Computer Vision (bonus)
What You'll Build
Examples of projects include:
- AI assistant that understands each client's project.
- AI chatbot trained on project documentation.
- AI support assistant.
- Internal company knowledge assistant.
- AI code/documentation assistant.
- AI-powered search engine.
- AI-generated reports.
- AI workflow automation.
Nice to Have
- Experience building AI SaaS products
- Experience deploying open-source LLMs
- Ollama
- vLLM
- Hugging Face
- LoRA fine-tuning
- GPU optimization
- CUDA
- Quantization
- Evaluation frameworks
- MCP servers
- CrewAI, AutoGen, or LangGraph
Ideal Candidate
- 3+ years of software development experience
- 2+ years of hands-on experience with LLMs and Generative AI
- Strong Python skills
- Experience building production AI applications
- Excellent problem-solving and communication skills
Pay: ₹35,000.00 - ₹50,000.00 per month
Work Location: In person
