5 Lang Graph Jobs

We are seeking a passionate and driven Generative AI Engineer to design, develop, and deploy innovative AI applications using Large Language Models (LLMs). The ideal candidate will have hands-on experience with prompt engineering, Python programming, and foundational knowledge of AI orchestration frameworks like LangChain and LangGraph. Experience with the Model Context Protocol (MCP) is a significant advantage. You will work closely with senior AI engineers and cross-functional teams to bring cutting-edge generative AI solutions to life Role & responsibilities Generative AI Application Development: Design, build, and deploy AI applications leveraging LLMs for various use cases such as RAG (Retrieval-Augmented Generation) based chatbots, intelligent agents, content generation, and more. Prompt Engineering: Develop, test, and optimize advanced prompt engineering techniques (e.g., few-shot, Chain-of-Thought, ReAct) to enhance LLM performance, accuracy, and user experience. LLM Orchestration with LangChain & LangGraph: Utilize LangChain and LangGraph to build robust, stateful, and multi-agent AI systems, managing complex conversational flows and integrating external tools and data sources. Python Development: Write clean, efficient, and well-documented Python code for AI model integration, data preprocessing, API development, and general application logic. Model Context Protocol (MCP): Implement and leverage MCP for seamless interaction between LLMs and external systems, ensuring efficient context management and secure communication (if applicable to project needs). Model Evaluation & Testing: Assist in evaluating the performance of generative AI models, defining relevant metrics, and conducting rigorous testing to ensure reliability and effectiveness. Collaboration: Work collaboratively with data scientists, machine learning engineers, product managers, and other stakeholders to translate business requirements into technical solutions. Research & Innovation: Stay updated with the latest advancements in generative AI, LLMs, and related frameworks, and actively experiment with new approaches to improve existing solutions. Deployment & MLOps (Basic): Contribute to the deployment of AI models and understand basic MLOps practices for model versioning, monitoring, and continuous improvement. . Required Qualifications: Bachelor's or Master's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or a related quantitative field. 1-3 years of hands-on experience in machine learning, software development, or data science, with exposure to AI/ML projects. Strong proficiency in Python programming and familiarity with relevant libraries (e.g., NumPy, Pandas). Proven experience with LangChain for building LLM-powered applications and chaining together various components. Familiarity with LangGraph for orchestrating complex, stateful multi-agent workflows. Hands-on experience with prompt engineering and optimizing prompts for LLMs. Understanding of Large Language Models (LLMs) and their underlying concepts. Experience or strong understanding of Model Context Protocol (MCP) for connecting LLMs with external tools and data sources. Excellent problem-solving skills and a proactive approach to challenges. Strong communication and interpersonal skills, with the ability to articulate technical concepts clearly.) Preferred Skills : Experience with cloud platforms (Azure, AWS, GCP) for deploying AI/ML solutions. Microsoft Certified: Azure AI Engineer Associate (AI-102) or similar AI/ML certification. Familiarity with vector databases (e.g., Pinecone, Chroma, FAISS). Experience with deep learning frameworks such as TensorFlow or PyTorch. Knowledge of Natural Language Processing (NLP) techniques beyond LLMs. Experience in building conversational AI systems or chatbots

Job Position (Title): Agentic AI Experience Required: 3 - 9 Years No of Position: 4 Job Type: FTE Location: Hyderabad Required Skills 3 to 7 years of hands-on experience in AI/ML, with at least 12 years specifically in Agentic AI or autonomous agents. Strong proficiency in Python and familiarity with AI libraries such as Hugging Face Transformers, LangChain, and OpenAI APIs. Experience with tools like AutoGen , CrewAI , and LangGraph . Deep understanding of RAG pipelines , LLM fine-tuning , and embedding-based retrieval systems . Hands-on experience with vector databases like FAISS, Pinecone, or similar. Solid foundation in machine learning, NLP, and data structures. Excellent communication skills and ability to work in a collaborative environment Role and Responsibilities Design, build, and deploy intelligent autonomous agents using Agentic AI frameworks like AutoGen , CrewAI , and LangGraph . Implement RAG (Retrieval-Augmented Generation) pipelines to enhance response accuracy and contextual relevance. Work with vector databases (e.g., FAISS, Pinecone, Weaviate) for knowledge storage and semantic search. Fine-tune large language models (LLMs) for specific tasks using tools like LoRA, PEFT, or full model training. Collaborate with product, research, and engineering teams to understand user needs and create agent-based workflows. Integrate APIs and services to create complex multi-agent systems capable of task delegation and coordination. Continuously evaluate and improve system performance, scalability, and reliability. Preferred Qualifications Prior experience deploying LLM-based agents in production. Knowledge of prompt engineering and agent orchestration. Contributions to open-source AI/agent frameworks.

Key Responsibilities: Agentic AI solution implementation leveraging Azure ecosystem, open-source RPA tools and scripting solutions where needed. Automation Solution Development : Create, deploy, and optimize automation workflows and BOTs using Agentic AI frameworks like Autogen. Leverage AI-driven processes to enable smart automation in business operations. Hands-on Cloud Integration : Design and implement automation solutions that integrate seamlessly with Microsoft Azure services (such as Azure Functions , Logic Apps , Azure Storage ) and other cloud-based tools to improve scalability and performance. AI and Python Libraries : Utilize Agentic AI frameworks for enhancing automation processes, and use Python libraries like Playwright for web automation, browser interaction, and testing. Implement machine learning models or AI algorithms where applicable to automate decision-making and data processing tasks. Scripting & Customization : Develop custom scripts in languages such as Python , PowerShell , JavaScript , and others to extend the functionality of RPA solutions, optimize workflows, and troubleshoot complex scenarios. Stakeholder Engagement : Collaborate with business analysts, IT teams, and key stakeholders to gather requirements, align automation goals with business priorities, and ensure automation solutions meet the desired business outcomes. Process Optimization : Continuously monitor, analyze, and optimize existing automation systems to enhance performance, reduce processing times, and ensure robustness. Identify opportunities to further automate manual processes across departments. Technical Leadership & Mentorship : Provide leadership, mentorship, and training to Agentic AI developers and junior engineers. Share best practices and foster a collaborative environment to ensure high standards of automation development.

Position Overview We are seeking AI Product Engineers with 12 years of experience who can bridge the gap between product development and advanced AI technologies. This role involves working closely with AI models, APIs, and data pipelines, while also contributing to product design, user experience, and deployment strategies. You will work at the intersection of technology , user experience , and business outcomes . Key Responsibilities Collaborate with product managers and AI teams to design and develop AI-driven products leveraging LLMs (GPT-3.5, GPT-4, Gemini). Translate business requirements into AI product features and work on building functional prototypes. Develop and integrate LangChain-based workflows, including LangSmith and LangGraph , to enable intelligent app interactions. Implement Retrieval-Augmented Generation (RAG) pipelines and integrate vector databases (e.g., ChromaDB) to enhance AI performance. Apply prompt engineering to customize model outputs based on product needs and use cases. Build REST APIs and microservices using Flask or FastAPI to support model integration. Work with SQL , PySpark , and Spark SQL to manage and process structured and unstructured data. Collaborate with UI/UX teams to ensure seamless user interaction with AI components. Support product deployment and monitoring on Azure ML or AWS Bedrock . Required Skills Strong programming skills in Python , SQL , PySpark , Spark SQL Understanding of Generative AI , LLMs , and prompt engineering Experience with LangChain , LangGraph , LangSmith Familiarity with vector databases and embedding techniques Exposure to cloud platforms : Azure ML or AWS Bedrock REST API development using Flask or FastAPI Excellent problem-solving skills and product-oriented mindset Preferred Qualifications Bachelor’s degree in Computer Science, AI/ML, Data Science, or related field Internship or academic experience in AI product development or applied NLP Familiarity with MLOps concepts and product lifecycle best practices Basic understanding of UI/UX principles and user-centric design

Role: AI/ML Engineer Has 4+ years of work experience , with at least 2+ years directly working on Generative AI and Agentic systems Knows how to use Large Language Models (LLMs) like GPT for real applications (not just research or theory) Has worked on multi-agent systems or autonomous AI agents using tools like CrewAI, AutoGen, or similar frameworks Can write smart prompts ( prompt engineering ), build apps with LLMs, and knows how to do RAG (Retrieval-Augmented Generation) Has done fine-tuning of models and built custom AI workflows Codes well in Python Has used ML frameworks like TensorFlow or PyTorch Familiar with tools like LangChain , and cloud/data platforms like AWS or Databricks Location: Bangalore/ Mumbai Shift Timing: 12:00 PM 9:00 PM Notice Period: 30 days or less Call Anumeha @ +91 6376649769/ Alfiya @ +91 8787064649