About the Role:
We are looking for a passionate and driven AI/ML Engineer with hands-on experience or strong interest in working with Large Language Models (LLMs), fine-tuning techniques, and LangChain framework integration. You will be responsible for building and optimizing intelligent agents, RAG pipelines, and dynamic workflows tailored for real-world applications in the blockchain and AI automation space.
Key Responsibilities:
- Fine-tune and train Large Language Models (LLMs) using open-source frameworks and proprietary datasets.
- Develop and deploy LangChain-based intelligent agents for custom workflows (RAG, Tool Calling, Memory).
- Implement Retrieval-Augmented Generation (RAG) pipelines using vector databases like FAISS, Chroma, Weaviate, or Qdrant.
- Work with Hugging Face Transformers, OpenAI/Anthropic APIs, and other foundation model platforms.
- Integrate prompt engineering techniques to enhance model outputs for agent tasks.
- Optimize training datasets and workflows for efficiency, accuracy, and scalability.
- Collaborate with backend teams to deploy models in containerized environments (Docker, FastAPI).
- Monitor performance metrics and continuously improve the models.
Required Skills:
- Strong understanding of Python and ML frameworks (PyTorch / TensorFlow).
- Familiarity with LLM APIs (OpenAI, Anthropic, Cohere, etc.)
- Hands-on experience or knowledge of LangChain and/or LangGraph.
- Experience in vector database integration for RAG pipelines.
- Basic knowledge of prompt engineering and model inference logic.
- Exposure to training or fine-tuning transformer-based models.
Nice to Have:
- Experience with model quantization (GGUF/GGML), LoRA, PEFT, or QLoRA.
- Exposure to Hugging Face ecosystem, including model hub and datasets.
- Experience with cloud infrastructure (AWS/GCP), Kubernetes, or GPU clusters.
- Familiarity with MLOps and model versioning practices.
Qualifications:
- B.Tech / M.Tech / B.Sc / M.Sc in Computer Science, AI, Data Science, or equivalent.
- Project portfolio, GitHub repo, or published demos is a plus (mention in resume).
Job Types: Full-time, Permanent
Work Location: In person/ WFH
Pay: ₹25,000.00 per month
Benefits:
- Paid sick time
- Paid time off
- Provident Fund
- Work from home
Application Question(s):
- How many years of Python experience do you have?
- Have you built applications using LangChain or LangGraph?
- Have you implemented a Retrieval-Augmented Generation (RAG) pipeline?
- When can you join?
Work Location: In person
