AI Agentic Engineer

· The ideal candidate will have hands-on experience and advanced proficiency in building and implementing AI agents using modern frameworks and architecture, including Langraph, LangChain, Vector Databases, RAG (Retrieval-Augmented Generation), and Multi-agent systems.

· This role demands strong expertise in Python programming and a deep understanding of AI systems capable of operating autonomously within complex environments.

Key Responsibilities:

· AI System Development Design and develop intelligent agents leveraging Langraph Framework and LangChain Architecture for modular and flexible AI systems. Architect and implement multi-agent systems where agents collaborate or compete to achieve predefined goals autonomously.

· Vector Databases & Retrieval-Augmented Generation Build scalable retrieval-augmented generation (RAG) pipelines to enable effective use of large language models for context-aware decision-making. Leverage Vector Databases (e.g., Pinecone, Weaviate, or Milvus) for efficient storage and retrieval of embeddings and massive datasets for real-time inference.

· Complex Workflow Integration Integrate AI agents with real-world workflows, APIs, and distributed infrastructures. Develop and deploy agents capable of acting within dynamic and ever-changing environments (e.g., multi-user systems or IoT networks).

· Programming & Algorithm Implementation Write optimized and maintainable Python code to create scalable AI models. Implement advanced NLP, machine learning, reasoning algorithms, and memory models using LangChain and similar architectures.

· Collaboration & Cloud Infrastructure Work with interdisciplinary teams to understand requirements and translate them into agentic architecture. Deploy models on cloud services (e.g., AWS, Azure, Google Cloud) while ensuring scalability and robust performance.

· Testing & Optimization Conduct rigorous testing of autonomous agent systems to identify and resolve edge cases. Continuously refine algorithms for efficiency, scalability, and ethical alignment.

Required Skills & Qualifications:

Must-Have Technical Expertise:

· Frameworks & Architectures: Proficiency in Langraph Framework and LangChain Architecture for AI agent orchestration. Demonstrated ability to design and scale lightweight, modular agentic systems. Familiarity with Agentic Memory Models and self-healing systems. Knowledge of LLM fine-tuning and natural language understanding (NLU).

· Vector Databases: Hands-on experience in configuring and utilizing vector databases such as Pinecone, Milvus, or FAISS for optimized storage and retrieval of high-dimensional embeddings., Weaviate, or FAISS. Familiarity with Postgres extensions (e.g., pgvector) for managing vector-based data in relational databases Proficiency with Azure Cognitive Search or other Azure-based vector database solutions for implementing scalable and enterprise-grade semantic search Strong understanding of semantic search, embedding-based indexing methods, and vector similarity search.

· RAG Implementation: Hands-on experience deploying Retrieval-Augmented Generation (RAG) workflows for enhanced LLM performance.

· Multi-agent Systems: Expertise in designing ecosystems of multi-agent architectures where agents interact in collaborative or adversarial scenarios.

· Programming: Advanced Python programming skills with a focus on building production-ready AI solutions.

· Cloud Technologies: Experience deploying AI systems on cloud platforms (e.g., Azure). Understanding of containerization (Docker, Kubernetes) for maintaining agent workflows

Pay: $60.00 - $65.00 per hour

Experience:

• Agentic AI: 2 years (Required)
• RAG: 2 years (Required)
• Langchain: 2 years (Required)

Work Location: Remote