Remote
Full-Time
India
Skills
Amazon Web Services (AWS)
Artificial Intelligence (AI)
Python (Programming Language)
Computer Science
TensorFlow
Machine Learning
Docker Products
Data Science
Deep Learning
File Systems
About the Role
We are looking for an AI Agent Developer to join our team and build intelligent, autonomous systems powered by Large Language Models (LLMs). You’ll work with modern frameworks like LangChain, AutoGPT, and CrewAI to create AI agents that can reason, plan, and interact with tools, APIs, and users.
This role is perfect for someone passionate about combining software engineering, machine learning, and prompt engineering to solve real-world problems with AI.
🔧
Responsibilities:
Build, test, and deploy LLM-powered AI agents using frameworks like LangChain, AutoGPT, BabyAGI, and CrewAI
Design agent workflows with memory, tool usage, retrieval mechanisms, and multi-step planning
Write clean, modular code in Python to build applications and APIs using FastAPI or Flask
Connect agents with external tools and APIs (e.g., web search, files, spreadsheets, SaaS platforms)
Integrate with vector databases (e.g., Pinecone, FAISS, Weaviate) for knowledge retrieval
Manage data flows using Pandas, NumPy, and SQL
Collaborate with ML and product teams to integrate agents into larger platforms or products
Skills & Qualifications:
Strong experience with Python
Familiarity with LLMs (OpenAI, Anthropic, LLaMA, etc.)
Experience with agent frameworks like LangChain, AutoGPT, CrewAI, BabyAGI
Understanding of prompt engineering and structured workflows
API development using FastAPI or Flask
Ability to work with external APIs, tools, and file systems
Experience with Docker and basic deployment pipelines
Nice to Have:
Knowledge of vector DBs (FAISS, Pinecone, etc.)
Experience deploying to AWS, GCP, or Azure
Background in ML model training with TensorFlow or PyTorch
Exposure to RAG, agent memory, and multi-agent collaboration
This role is perfect for someone passionate about combining software engineering, machine learning, and prompt engineering to solve real-world problems with AI.
🔧
Responsibilities:
Build, test, and deploy LLM-powered AI agents using frameworks like LangChain, AutoGPT, BabyAGI, and CrewAI
Design agent workflows with memory, tool usage, retrieval mechanisms, and multi-step planning
Write clean, modular code in Python to build applications and APIs using FastAPI or Flask
Connect agents with external tools and APIs (e.g., web search, files, spreadsheets, SaaS platforms)
Integrate with vector databases (e.g., Pinecone, FAISS, Weaviate) for knowledge retrieval
Manage data flows using Pandas, NumPy, and SQL
Collaborate with ML and product teams to integrate agents into larger platforms or products
Skills & Qualifications:
Strong experience with Python
Familiarity with LLMs (OpenAI, Anthropic, LLaMA, etc.)
Experience with agent frameworks like LangChain, AutoGPT, CrewAI, BabyAGI
Understanding of prompt engineering and structured workflows
API development using FastAPI or Flask
Ability to work with external APIs, tools, and file systems
Experience with Docker and basic deployment pipelines
Nice to Have:
Knowledge of vector DBs (FAISS, Pinecone, etc.)
Experience deploying to AWS, GCP, or Azure
Background in ML model training with TensorFlow or PyTorch
Exposure to RAG, agent memory, and multi-agent collaboration
Apply for this position
Application Status
Application Draft
In Progress
Submit Application
Pending
Review Process
Expected within 5-7 days
Similar Jobs
