Posted on: 22/05/2025
Job Summary :
Key Responsibilities :
- Develop and optimize RAG (Retrieval-Augmented Generation) pipelines using LangChain or similar frameworks.
- Integrate and fine-tune OpenAI/GPT-like models for various business applications.
- Apply NLP and Deep Learning techniques to extract insights and build intelligent features.
- Write clean, modular, and scalable code in Python, including API design and integration.
- Deploy ML models and applications to the cloud using AWS, GCP, or Azure.
- Work with vector databases (e.g., FAISS, Pinecone, Weaviate) and embeddings for semantic search and retrieval.
- Utilize Docker and containerization for environment consistency and deployment workflows.
- Collaborate with cross-functional teams including data scientists, backend engineers, and product managers.
Required Skills & Qualifications :
- Proficiency in LangChain, RAG architecture, and LLM orchestration.
- Strong knowledge of OpenAI APIs or equivalent large language models (e.g., Cohere, Claude, LLaMA).
- Solid understanding of NLP, deep learning, and transformer-based architectures.
- Advanced Python programming skills and experience building APIs (FastAPI, Flask, etc.).
- Experience deploying ML/AI solutions on AWS, Azure, or Google Cloud.
- Hands-on experience with vector stores and embedding models.
- Proficiency with Docker, version control (Git), and CI/CD pipelines.
Preferred Qualifications :
- Masters or PhD in Computer Science, Machine Learning, AI, or related fields.
- Experience with MLOps and model monitoring tools.
Did you find something suspicious?
Posted By
Posted in
AI/ML
Functional Area
ML / DL Engineering
Job Code
1483712
Interview Questions for you
View All