82 Langgraph Jobs - Page 4

Responsibilities: * Develop cutting-edge Agentic AI solutions using Langchain, Langgraph & OpenAI technologies. * Collaborate with cross-functional teams on project delivery and knowledge sharing. Health insurance Work from home

Required Skills 7+ years of professional Python development experience Hands-on experience with at least one agent framework (CrewAI, LangChain, LangGraph, or equivalent) Strong understanding of LLM capabilities, limitations, and prompt engineering Experience with RESTful API design and async Python (FastAPI preferred) Knowledge of vector databases and RAG (Retrieval Augmented Generation) systems Familiarity with financial or tax domains Demonstrated leadership in technical decision-making Excellent written and verbal communication skills Nice to Have Experience with AWS services, particularly Lambda and EKS Background in financial services or tax preparation software Knowledge of security and compliance requirements for financial data Previous startup experience, particularly in MVP development

We are seeking a skilled, motivated, and quick-learner Full Stack Developer to join our team working on cutting-edge Gen AI development work. The successful candidate will be responsible for developing innovative applications and solutions using including frontend and backend. While the solutions will often utilize Retrieval Augmented Generation (RAG), Agentic frameworks the role will not be limited to this, and will involve various AI technologies. Develop and maintain web applications using Angular, NDBX frameworks, and other modern technologies. Design and implement databases in Postgres DB, apply & implement ingestion and retrieval pipelines using pgvector, neo4j, ensuring efficient and secure data practices. Use different generative AI models & frameworks such as LangChain, Haystack, LlamIndex etc for chucking, embeddings, chat completions, integration with different data sources etc. Familiarity and experience with different agentic frameworks and technique like Langgraph, AutoGen, CrewAI, tool using techniques like MCP (Model Context Protocol). Use Azure & AWS cloud platforms in implementation to stay relevant to company AI guidelines requirements. Usage of OpenAPI standards, API first approach to develop APIs for communication between different software components. Collaborate with the team members to integrate various GenAI capabilities into the applications, including but not limited to RAG. Write clean, maintainable, and efficient code that adheres to company standards. Conduct testing to identify and fix bugs or vulnerabilities. Use collaboration and versioning tools such as GitHub for effective team working and code management. Stay updated with emerging technologies and apply them into operations and activities. Show a strong desire for continuous learning and the ability to quickly adapt and implement new technologies. Bachelor's degree in Computer Science, Information Technology, or a related field with 6+ years of working experience. Proven experience as a Full Stack Developer or similar role in designing, developing and deploying end to end applications. Knowledge of multiple front-end languages and libraries (e.g. HTML/ CSS, JavaScript, XML, jQuery). Experience with Angular and NDBX frameworks. Good experience with database technology such as Postgres DB, vector databases. Experience developing APIs following the OpenAPI standards. Understanding & experience in various generative AI models on cloud platforms such as Azure/ AWS, including Retrieval Augmented Generation, Prompt engineering, Agentic RAG, Agentic frameworks, Model context protocols etc. Experience with collaboration and versioning tools such as GitHub Experience with docker images, containers to package up an application with all the parts it needs, such as libraries and other dependencies, and ship it all out as one package. Functional Demonstrated responsiveness and accuracy Strong collaboration and teamwork skills Behaviours Take Ownership & Accountability Assertiveness & Persuasiveness Great attention to detail and problem-solving skills. Self-motivated with a keen interest in learning and implementing new technologies.

Job Type: Full Time Job Description: We are seeking an experienced AI Engineer with 4-5 years of hands-on experience in designing and implementing AI solutions. The ideal candidate should have a strong foundation in developing AI/ML-based solutions, including expertise in Computer Vision (OpenCV). Additionally, proficiency in developing, fine-tuning, and deploying Large Language Models (LLMs) is essential. As an AI Engineer, candidate will work on cutting-edge AI applications, using LLMs like GPT, LLaMA, or custom fine-tuned models to build intelligent, scalable, and impactful solutions. candidate will collaborate closely with Product, Data Science, and Engineering teams to define, develop, and optimize AI/ML models for real-world business applications. Key Responsibilities: Research, design, and develop AI/ML solutions for real-world business applications, RAG is must. Collaborate with Product & Data Science teams to define core AI/ML platform features. Analyze business requirements and identify pre-trained models that align with use cases. Work with multi-agent AI frameworks like LangChain, LangGraph, and LlamaIndex. Train and fine-tune LLMs (GPT, LLaMA, Gemini, etc.) for domain-specific tasks. Implement Retrieval-Augmented Generation (RAG) workflows and optimize LLM inference. Develop NLP-based GenAI applications, including chatbots, document automation, and AI agents. Preprocess, clean, and analyze large datasets to train and improve AI models. Optimize LLM inference speed, memory efficiency, and resource utilization. Deploy AI models in cloud environments (AWS, Azure, GCP) or on-premises infrastructure. Develop APIs, pipelines, and frameworks for integrating AI solutions into products. Conduct performance evaluations and fine-tune models for accuracy, latency, and scalability. Stay updated with advancements in AI, ML, and GenAI technologies. Required Skills & Experience: AI & Machine Learning: Strong experience in developing & deploying AI/ML models. Generative AI & LLMs: Expertise in LLM pretraining, fine-tuning, and optimization. NLP & Computer Vision: Hands-on experience in NLP, Transformers, OpenCV, YOLO, R-CNN. AI Agents & Multi-Agent Frameworks: Experience with LangChain, LangGraph, LlamaIndex. Deep Learning & Frameworks: Proficiency in TensorFlow, PyTorch, Keras. Cloud & Infrastructure: Strong knowledge of AWS, Azure, or GCP for AI deployment. Model Optimization: Experience in LLM inference optimization for speed & memory efficiency. Programming & Development: Proficiency in Python and experience in API development. Statistical & ML Techniques: Knowledge of Regression, Classification, Clustering, SVMs, Decision Trees, Neural Networks. Debugging & Performance Tuning: Strong skills in unit testing, debugging, and model evaluation. Hands-on experience with Vector Databases (FAISS, ChromaDB, Weaviate, Pinecone). Good to Have: Experience with multi-modal AI (text, image, video, speech processing). Familiarity with containerization (Docker, Kubernetes) and model serving (FastAPI, Flask, Triton).

Role & responsibilities Expertise in Data Analysis, Statistics, Computer Vision, AI & Machine Learning Concepts Unflinching zeal to learn, to try out Proof of Technology for new and emerging AI/ML Design and develop applications powered by Large Language Models (LLMs) like GPT-4, Claude, Gemini, and open-source models (LLaMA, Mistral, etc.) Implement RAG pipelines using LangChain and LangGraph for production-ready applications. Build and orchestrate autonomous and tool-using LLM agents. Integrate with vector databases (e.g., Pinecone, Chroma, Weaviate, FAISS) for semantic search and memory storage. Use tools like OpenAI Function Calling, React, or LangGraph Agents for decision-based workflows. Deploy applications using cloud platforms (Azure, AWS, GCP) with APIs, microservices, or serverless functions. Collaborate with product and design teams to develop chatbots, copilots, and multimodal interfaces. Monitor performance, cost, latency, and evaluate prompt effectiveness through prompt engineering best practices. Fine-tune, quantize, or use adapters (LoRA, PEFT) for open-source models where applicable. Stay up-to-date with the latest advancements in Gen AI, MLOps, and AI safety principles. Preferred candidate profile Bachelor's/Master's degree in Computer Science, Mathematics, Statistics, or a related field. 4-9 years of experience as a Data Scientist with strong skills in Python, NLP, Deep Learning, and Statistics. Hands-on experience with Generative AI, LangChain, LangGraph, and building LLM Agents for real-world AI applications. Strong Python skills with experience in deploying Gen AI apps using frameworks like FastAPI or Streamlit. Expertise in Retrieval-Augmented Generation (RAG) and working with vector databases like Pinecone, FAISS, or Chroma. Deep understanding of prompt engineering, OpenAI function calling, and chaining logic for dynamic interactions. Familiarity with cloud platforms such as Azure and AWS and deploying models to these platforms. Strong problem-solving and analytical skills with excellent communication and presentation skills. Disclaimer: The following job description serves as an informative reference for the tasks you may be required to perform. However, it does not constitute an integral component of your employment agreement and is subject to periodic modifications to align with evolving circumstances

Role & responsibilities Preferred candidate profile We're seeking a skilled Python developer with a focus on building advanced agentic applications. In this role, you'll architect and implement autonomous AI systems that can reason, plan, and execute complex tasks with minimal human intervention. Core Responsibilities Design and develop agentic AI applications using Python and modern frameworks Implement and optimize Retrieval-Augmented Generation (RAG) systems for knowledge-intensive applications Create scalable backend services using FastAPI and Django Collaborate with cross-functional teams to define agent architectures and workflows Develop testing frameworks to evaluate agent performance and reliability Document technical approaches, system architectures, and implementation details Technical Requirements Strong proficiency in Python programming and software engineering best practices Experience building web applications with FastAPI and/or Django frameworks Practical experience implementing RAG systems and understanding of vector databases Familiarity with prompt engineering techniques and LLM capabilities/limitations Knowledge of containerization, CI/CD pipelines, and deployment strategies Nice-to-Have Skills Experience with agentic frameworks like LangGraph or CrewAI Background in fine-tuning open-source models (e.g., Llama, Mistral, Falcon) Understanding of multi-agent systems and coordination protocols Experience with tools like LlamaIndex, LangChain, or similar LLM orchestration libraries Familiarity with reinforcement learning from human feedback (RLHF) Contributions to open-source AI projects Technical Environment You'll be working with cutting-edge technologies including: Python 3.x ecosystem FastAPI and Django for backend development Vector databases (e.g., Pinecone, Milvus, or Weaviate) LLM orchestration frameworks Modern cloud infrastructure (AWS/GCP/Azure) What We're Looking For Problem solvers who enjoy tackling complex technical challenges Self-motivated learners who stay current with rapidly evolving AI technologies Engineers who can balance theoretical understanding with practical implementation Strong communicators who can explain technical concepts to various stakeholders Join us to push the boundaries of what's possible with agentic AI systems and help shape the future of autonomous applications.

What Youll Own Full Stack Systems: Architect and build end-to-end applications using Flask, FastAPI, Node.js, React (or Next.js), and Tailwind. AI Integrations: Build and optimize pipelines involving LLMs (OpenAI, Groq, LLaMA), Whisper, TTS, embeddings, RAG, LangChain, LangGraph, and vector DBs like Pinecone/Milvus. Cloud Infrastructure: Deploy, monitor, and scale systems on AWS/GCP using EC2, S3, IAM, Lambda, Kafka, and ClickHouse. Real-time Systems: Design asynchronous workflows (Kafka, Celery, WebSockets) for voice-based agents, event tracking, or search indexing. System Orchestration: Set up scalable infra with autoscaling groups, Docker, and Kubernetes (PoC ready, if not full prod). Growth-Ready Features: Implement in-app nudges, tracking with Amplitude, AB testing, and funnel optimization. Tech Stack Youll Work With: Backend & Infrastructure Languages/Frameworks: Python (Flask, FastAPI), Node.js Databases: PostgreSQL, Redis, ClickHouse Infra: Kafka, Docker, Kubernetes, GitHub Actions, Cloudflare Cloud: AWS (EC2, S3, RDS), GCP Frontend React / Next.js, TailwindCSS, Zustand, Shadcn/UI WebGL, Three.js for 3D rendering AI/ML & Computer Vision LangChain, LangGraph, HuggingFace, OpenAI, Groq Whisper (ASR), Eleven Labs (TTS) Diffusion Models, StyleGAN, Stable Diffusion GANs, MediaPipe, ARKit/ARCore Computer Vision: Face tracking, real-time try-on, pose estimation Virtual Try-On: Face/body detection, cloth/hairstyle try-ons APIs Stripe, VAPI, Algolia, OpenAI, Amplitude Vector DB & Search Pinecone, Milvus (Zilliz), custom vector search pipelines Other Vibe Coding culture, prompt engineering, system-level optimization Must-Haves: 1+ years of experience building production-grade full-stack systems Fluency in Python and JS/TS (Node.js, React) shipping independently without handholding Deep understanding of LLM pipelines, embeddings, vector search, and retrieval-augmented generation (RAG) Experience with AR frameworks (ARKit, ARCore), 3D rendering (Three.js), and real-time computer vision (MediaPipe) Strong grasp of modern AI model architectures: Diffusion Models, GANs, AI Agent Hands-on with system debugging, performance profiling, infra cost optimization Comfort with ambiguity fast iteration, shipping prototypes, breaking things to learn faster Bonus if youve built agentic apps, AI workflows, or virtual try-ons