Full Time
700
29
Feb 6, 2026
We are seeking a highly experienced AI engineer specializing in the design, development, and deployment of LLM-based agents and autonomous AI systems.
This role is not focused on web development, SEO, UI, or general software engineering. It is a deeply technical position for engineers whose core expertise is AI agents, reasoning systems, and large language model orchestration.
Role Overview
You will design and build production-grade AI agents capable of executing complex tasks with minimal supervision. This includes single-agent and multi-agent systems with structured reasoning, memory, tool use, and robust failure handling.
Key Responsibilities
Architect and implement LLM-driven autonomous agents
Build multi-agent systems with coordination, delegation, and feedback loops
Design structured reasoning pipelines (planning, execution, reflection)
Implement long-term and short-ter
Integrate tool calling, function execution, and external APIs
Develop Retrieval-Augmented Generation (RAG) systems using vector databases
Debug and mitigate hallucinations, looping behaviors, and reasoning failures
Optimize systems for reliability, latency, cost, and scalability
Required Technical Expertise
Advanced Python engineering (clean, modular, production-ready code)
Deep hands-on experience with OpenAI / GPT-4 / GPT-4.1 / o-series models
Strong understanding of LLM prompting at a system and architectural level
Practical experience with agent frameworks, such as:
LangChain / LangGraph
AutoGen
CrewAI
or equivalent custom implementations
Expertise in embeddings, semantic search, and vector databases:
Pinecone, Weaviate, FAISS, Chroma, or similar
Experience designing and evaluating RAG pipelines
Familiarity with LLM evaluation, observability, and agent debugging
Strongly Preferred Qualifications
Experience deploying AI agents in real-world or production environments
Ability to reason about failure modes, edge cases, and system behavior
Comfort designing AI architectures without reliance on templates or tutorials
Strong understanding of LLM limitations and trade-offs
Ability to clearly explain technical decisions and system designs
What This Role Is Not
Not web development (frontend or backend)
Not SEO, marketing, or automation scripting
Not prompt-only experimentation
Not entry-level or exploratory AI work
Application Requirements
Applicants should submit:
A summary of AI agents or LLM systems they have built
Relevant code samples, repositories, or architecture diagrams
A brief explanation of a challenging AI system problem they encountered and how they solved it