Senior AI Engineer
Senior AI Engineer
We're looking for an exceptional AI Engineer who can take AI products from idea to production. This is not a prompt-engineering role. We need someone who deeply understands modern AI systems, can conduct research, design architectures, build production-grade solutions, and deploy scalable AI products used by real users.
You will be expected to work across the entire AI stack: research, experimentation, agent systems, RAG, backend engineering, infrastructure, deployment, optimization, and monitoring.
What You'll Do
- Design and build AI-powered products from scratch, from concept to production.
- Research and evaluate new AI technologies, frameworks, models, and architectures.
- Build advanced AI agents capable of reasoning, planning, tool usage, memory management, and multi-step task execution.
- Design and implement sophisticated RAG systems with retrieval optimization, hybrid search, reranking, memory, and knowledge management.
- Architect end-to-end AI workflows, orchestration systems, and autonomous agent pipelines.
- Integrate LLMs with APIs, databases, third-party services, and enterprise systems.
- Deploy and maintain production-grade AI infrastructure with reliability, scalability, and observability in mind.
- Optimize model performance, latency, cost, context management, and inference workflows.
- Design evaluation frameworks, benchmarking systems, and AI quality monitoring.
- Work closely with product and business teams to rapidly experiment, validate ideas, and ship features.
- Drive technical decisions related to AI architecture and long-term platform strategy.
- Stay ahead of developments in the AI ecosystem and continuously introduce new approaches when beneficial.
Requirements
- Strong software engineering background with proven experience building production systems.
- Expert-level Python skills and solid backend engineering fundamentals.
- Deep understanding of LLMs, AI agents, RAG architectures, embeddings, vector databases, and orchestration frameworks.
- Experience designing and deploying production AI applications used by real users.
- Strong understanding of prompt engineering, context management, tool calling, memory systems, and agent planning.
- Experience building scalable backend services, APIs, asynchronous systems, and distributed architectures.
- Familiarity with cloud infrastructure and deployment workflows.
- Ability to independently research unfamiliar problems and turn findings into working solutions.
- Strong system design, debugging, and problem-solving skills.
- Comfortable working in fast-moving environments with high ownership.
Preferred Experience
- Experience with LangGraph, OpenAI SDK, MCP, AutoGen, CrewAI, OpenHands, OpenClaw, or similar agent frameworks.
- Experience building autonomous agents and multi-agent systems.
- Experience with local and self-hosted models (Llama, Qwen, DeepSeek, Mistral, etc.).
- Experience with vector databases, knowledge retrieval systems, and search infrastructure.
- Experience with Docker, Kubernetes, Redis, PostgreSQL, message queues, and distributed systems.
- Experience with AI evaluation, guardrails, observability, and monitoring.
- Understanding of AI security, prompt injection, jailbreaking, sandboxing, and agent safety.
- Experience fine-tuning models, synthetic data generation, or AI research projects is a strong plus.