Senior AI Engineer — Agentic AI & Intelligent Systems
What You’ll Do
Architect and lead the development of AI-native platforms leveraging foundation models such as OpenAI, Anthropic, Gemini, Mistral, and open-source LLMs.
Design and implement advanced multi-agent systems using frameworks such as LangGraph, CrewAI, AutoGen, and custom orchestration layers.
Build scalable Retrieval-Augmented Generation (RAG) systems with advanced retrieval strategies, semantic memory, and contextual reasoning.
Architect vector-search infrastructure using Pinecone, Qdrant, Weaviate, FAISS, or hybrid retrieval systems.
Lead end-to-end development of production-grade AI microservices using Python, FastAPI, and event-driven architectures.
Establish AI evaluation and observability pipelines using Ragas, DeepEval, LangSmith, and Weights & Biases.
Lead deployment and infrastructure strategies for scalable AI systems using Docker, Kubernetes, BentoML, and Ray Serve.
Optimize AI systems for latency, throughput, cost efficiency, reliability, and security in high-scale production.
What We’re Looking For
Education: Bachelor’s or Master’s degree in Computer Science, Artificial Intelligence, Software Engineering, or a related field.
Experience: 5+ years of professional software engineering experience with at least 3+ years focused on AI/ML systems and LLM-based applications.
Technical Mastery: Expert-level proficiency in Python and building scalable APIs using FastAPI or Flask.
AI Expertise: Deep understanding of modern foundation models, prompt engineering, context management, and agentic AI patterns.
Orchestration: Hands-on experience with LangChain, LangGraph, CrewAI, AutoGen, or equivalent frameworks.
Infrastructure: Experience deploying and monitoring AI workloads using Kubernetes, Docker, MLflow, and CI/CD pipelines.
Application Question(s):
Rate your expertise in Python, Lang Graph/CrewAI, and Vector Databases (1-10) and mention which LLMs (e.g., GPT-4, Llama, Gemini) you have deployed in production.
Describe a specific AI/ML project you led, focusing on how you handled RAG architectures or multi-agent orchestration