10 months ago
Bengaluru, IndiaSenior
Responsibilities
- Build and deploy LLM-powered agents for internal tools and customer-facing products.
- Design and improve RAG pipelines, prompt engineering workflows, and tool integrations.
- Experiment with open-source and closed-source LLMs.
- Implement and evaluate reasoning, planning, memory, and retrieval modules for AI agents.
- Optimize ML and LLM systems for accuracy, latency, scalability, and cost.
- Build production-ready AI/NLP pipelines with monitoring, evaluation benchmarks, and continual improvement loops.
- Collaborate with product, engineering, and customer-facing teams to ship AI features.
Requirements
- Bachelor's, master's, or doctoral degree in computer science or a mathematics-related field from a tier-1 engineering institute.
- 3+ years of industry experience in machine learning and NLP or applied AI.
- Strong programming skills in Python.
- Interest and experience with RAG and agentic AI concepts.
- Experience with PyTorch, Hugging Face Transformers, and similar ML libraries.
- Interest and experience in model training, inference optimization, and GPUs.
- Experience deploying ML services using REST APIs, Docker, Kubernetes, or cloud platforms.
- Exposure to vector databases such as FAISS, Pinecone, Qdrant, or similar.
Tech Stack
Categories
