AI Engineers at AppStoneLab focus on building intelligent agentic workflows using large language models (LLMs) and tools like LangGraph, LangChain, and OpenAI APIs. You’ll work closely with product and engineering teams to design prompt-based systems, automate tasks using LLMs, and create scalable AI-driven solutions. The ideal candidate is curious, pragmatic, and passionate about crafting AI agents that solve real-world problems without needing complex model fine-tuning.
Responsibility
Take ownership of AI/ML projects from ideation to deployment
Design and implement agentic workflows using frameworks like LangGraph and LangChain
Build modular AI agents that can plan, reason, and execute multi-step tasks
Create, test, and optimize structured prompts for various LLM-driven use cases
Integrate LLMs with tools via function calling / tool usage for dynamic workflows
Build intelligent APIs using Flask or FastAPI for production environments
Collaborate with product, design, and engineering teams to integrate AI systems
Work on NLP, computer vision, and recommendation-based tasks
Analyze large datasets and perform data preprocessing and feature engineering
Monitor and optimize performance of deployed models and agent workflows
Continuously explore and experiment with emerging LLM capabilities, multi-agent setups, and task orchestration strategies
Stay up to date with advancements in agentic systems, memory management, and RAG (Retrieval-Augmented Generation)
Requirements
Bachelor's degree in Computer Science, Data Science, or a related technical field
0–1 years of hands-on experience in AI/ML or LLM application development
Experience with at least one agentic AI framework (LangGraph, LangChain, AutoGen, or similar)
Solid Python development experience
Understanding of LLM architecture, prompt chaining, memory, and function/tool calling
Knowledge of cloud platforms like AWS/GCP is a plus
Experience in deploying ML models and/or AI agents into production workflows
Skills And Qualifications
Understanding of AI/ML/DL principles and practical application
Hands-on experience with AI agent frameworks, task orchestration, and autonomous loop execution
Knowledge of function calling, tool use, and building context-aware agents
Exposure to multi-agent systems, memory strategies, and prompt engineering
Familiarity with LangGraph stateful execution flows is a strong plus
Bonus: Understanding of RAG pipelines, vector databases (e.g., Pinecone, Weaviate)
Strong problem-solving skills and ability to think in flows rather than just models
Good communication skills and ability to explain AI logic in product terms
Education and Experience Requirements
Bachelor’s degree in Computer Science, AI, or related technical field.
Portfolio of AI projects or contributions (GitHub, Kaggle, etc.).
Experience with tools like TensorFlow, PyTorch, Scikit-learn.
Familiarity with API development using Flask or FastAPI.
Knowledge of cloud computing and deployment pipelines is a plus.