MightyBot - AI Engineer
Upload My Resume
Drop here or click to browse · PDF, DOCX, DOC, RTF, TXT
Requirements
• 1-3 years of experience in Software Engineering or end-to-end Data Science, with strong proficiency in Python and data-oriented algorithms. • Strong background in either distributed AI agents, data systems or machine learning engineering. • Modern Python microservices with FastAPI, Ray.IO for distributed AI workloads, and Kubernetes orchestration - powering enterprise-scale AI agent execution with gRPC inter-service communication and Google Cloud Pub/Sub event streaming • AI Agent Stack: LlamaIndex, LangGraph, SmolAgent, Instructor, Anthropic, OpenAI, Qdrant, ParadeDB, Sentence-Transformers, FAISS - building sophisticated AI agent orchestration with tool coordination, vector search, and real-time data processing • Recent demonstrated experience in building agents, training and evaluating emerging LLMs, building RAG systems, or working with vector databases. We encourage you to share your projects with us! • Familiarity with our core technologies is a plus: Ray, Postgres, Iceberg, Google Cloud, and Docker/Kubernetes/Helm. • Our Team • We are a rapidly growing startup with a high-performance engineering culture that emphasizes personal accountability, autonomy, learning, and growth. Led by experienced founders, our approach is design-centric, underpinned by market analysis, user research, and a dedication to scientific thinking and automation. We value intelligence, respectful collaboration, and SHIPPING CODE!
Responsibilities
• Build AI-Enabled Products: Develop products that are fully enabled by the capabilities of LLMs and other recent developments in foundation models. You will evaluate and assimilate emerging techniques into our production systems. • Build AI-Enabled Products: • High-Performance Search and RAG: Build and optimize our data indexing, ranking, and query processing systems for high-performance Search and Retrieval-Augmented Generation (RAG). • High-Performance Search and RAG: • Develop Evaluation Frameworks: Create robust frameworks to evaluate the performance of our agents, RAG systems, and various LLMs. We take a polyglot approach to working with LLMs, with a strong preference for getting workloads running on open-source models. • Develop Evaluation Frameworks:
No credit card. Takes 10 seconds.