About the role
We are seeking a highly skilled Generative AI Developer to join our AI innovation team. The ideal candidate will have hands-on experience in designing and deploying LLM-powered applications, building RAG pipelines, fine-tuning models using LoRA/Quantization, and implementing multi-agent workflows. If you're passionate about building intelligent systems that power real-world educational and analytical tools, this is your opportunity to innovate with us.
Shift : Day shift ( 10 am - 7 pm)
Monday to Friday
Key Responsibilities:
- Build and optimize LLM-based applications using frameworks like LangChain, Hugging Face, CrewAI, LangGraph, and LlamaIndex.
- Develop and maintain RAG (Retrieval-Augmented Generation) pipelines using vector databases like Pinecone, Astra DB, Chroma to improve retrieval accuracy.
- Fine-tune models (e.g., Llama3, Mistral) using techniques such as LoRA, Quantization, and PEFT to enhance performance and reduce latency.
- Design agentic AI systems using multi-agent coordination strategies for tasks such as automated content generation and evaluation.
- Work with prompt engineering to personalize user interactions.
- Deploy scalable AI systems using FastAPI/Flask, Docker, and AWS (SageMaker, Bedrock, EC2, S3).
- Collaborate with data science and product teams to turn concepts into production-ready solutions.
Required Skills & Qualifications:
- 2+ years experience in Generative AI / LLM Development.
- Proficiency in Python and SQL.
- Strong background in LLM fine-tuning, Prompt Engineering, and NLP evaluation techniques (ROUGE, BLEU, TF-IDF).
- Experience with FastAPI/Flask, MySQL, MongoDB, and cloud services (AWS/GCP/Azure).
- Hands-on experience with MLOps tools such as MLflow, Weights & Biases, CI/CD, and containerization using Docker.
- Degree in Computer Science, Engineering, or a related field.
BenefitsSalary Package : 6 LPA to 7 LPA