Sr. Artificial Intelligence Engineer

JOB PURPOSE

We are seeking a Senior Context Engineer to lead the design, development, and deployment of advanced AI systems and agentic workflows. This role focuses entirely on artificial intelligence technologies, with an emphasis on leveraging context-aware architectures, orchestration frameworks, and large language models (LLMs) to build production-grade AI solutions.

You will architect intelligent systems using tools such as LangChain, LangGraph, and vector databases, and integrate state-of-the-art APIs including OpenAI, Claude, Hugging Face, and more. This role requires a deep understanding of AI agents, memory management, embedding pipelines, and conversational orchestration. You will be a core contributor to building the infrastructure that powers next-generation, context-rich AI applications.

JOB RESPONSIBILITIES

·      Architect and implement intelligent AI workflows and agents using LangChain, LangGraph, or similar frameworks

·      Orchestrate multi-step reasoning processes, tool use, and context memory via LLMs

·      Build and maintain embedding pipelines using vector databases (e.g., Pinecone, Weaviate, Azure AI Search)

·      Develop backend services and orchestrators using Python and for managing AI interactions

·      Integrate with LLM APIs (OpenAI, Claude, Cohere, Mistral, etc.) and third-party flow builders (e.g., Flowise, Cognosys, custom GPTs)

·      Implement memory systems that support conversational persistence, summarization, and retrieval

·      Design and prototype novel agentic behaviors including autonomous task decomposition, recursive feedback loops, and real-time interactions

·      Contribute to scalable and modular deployment of AI services using serverless infrastructure, Docker, and CI/CD pipelines

·      Collaborate cross-functionally to scope, prioritize, and deliver AI-first features and research-driven prototypes

·      Write high-quality, well-documented code and maintain production-rxweadiness across systems

Essential skills

·      Proficiency in Python and/or for AI pipeline orchestration

·      Strong experience building AI agents with LangChain, LangGraph, or custom frameworks

·      Deep understanding of embeddings, retrieval augmentation (RAG), and vector stores

·      Familiarity with memory persistence patterns, summarization chains, and context window optimization

·      Experience integrating LLM APIs (OpenAI, Claude, Cohere, etc.) and leveraging their function-calling or tool-use capabilities

·      Hands-on experience with AI flow builders like Flowise, Cognosys, or OpenAI GPTs

·      Comfortable building robust backend systems to support LLM applications

·      Understanding of API design, authentication, and data modeling for AI services

·      Agile team collaboration using JIRA and Git-based workflows

Desirable skills

·      Experience with LangGraph or LlamaIndex for agentic and retrieval-based architectures

·      Familiarity with real-time AI interactions using WebSockets or streaming APIs

·      Understanding of serverless deployments (e.g., AWS Lambda, Vercel, Azure Functions)

·      Exposure to observability tools for monitoring LLM behavior and prompt performance

·      Knowledge of automation platforms like Zapier or n8n to augment AI pipelines

·      Understanding of cloud infrastructure, containerization (Docker), and scalable deployments

·      Interest in emerging AI safety, alignment, and control techniques

REQUIRED EXPERIENCE

(To perform this job successfully, an individual must be able to perform each essential duty satisfactorily. The requirements listed below are representative of the knowledge and experience required.)

Experience

· years in backend engineering with a strong emphasis on AI system design

· years of hands-on experience building and deploying AI agents or LLM-based tools

·      Demonstrated ability to build memory-aware, multi-turn AI workflows in production

·      Proven track record integrating APIs from OpenAI, Claude, Hugging Face, or similar

·      Experience working with vector databases and embedding-based retrieval systems

·      Track record of contributing to AI-first products in an agile development environment