Artificial Intelligence Engineer

We are looking for a highly skilled Mid-Senior AI Engineer with hands-on experience in building LLM-powered agent systems and conversational AI solutions. In this role, you will contribute to the architecture, development, and optimization of AI systems that enable users to interact with data through natural language.

You will work closely with a technically strong and fast-moving team, playing an active role in designing scalable multi-agent architectures, improving model reliability, and building production-grade AI applications.

Key Responsibilities

• Design and develop agentic AI systems using orchestration frameworks such as LangChain, LangGraph, and similar technologies
• Build and manage scalable multi-agent architectures and workflows
• Develop secure and reliable Text-to-SQL / NL2SQL pipelines that convert natural language queries into optimized SQL queries
• Integrate API-based LLMs such as OpenAI, Anthropic, Gemini, and Mistral, as well as local model infrastructures including Ollama, vLLM, and llama.cpp
• Implement observability and monitoring solutions using LangSmith, Langfuse, or similar tools for tracing, logging, telemetry, and production debugging
• Build and maintain evaluation frameworks to monitor model accuracy, hallucination rates, latency, and operational costs
• Apply AI security best practices including prompt injection prevention, access controls, content filtering, and guardrails
• Design and implement complex multi-step agent workflows
• Optimize prompts and contribute to fine-tuning workflows when necessary
• Participate actively in code reviews, technical discussions, and architecture decisions
• Prepare and maintain technical documentation and development standards

Required Qualifications

• Proven production-level experience with LangChain and/or LangGraph
• Strong hands-on experience designing and managing multi-agent AI systems
• Practical experience working on Text-to-SQL or NL2SQL projects
• Advanced SQL skills, including complex query writing, query optimization, and database schema understanding
• Strong experience integrating API-based LLM providers such as OpenAI, Anthropic, Gemini, or Mistral
• Experience running and managing local LLM infrastructures such as Ollama, vLLM, llama.cpp, or similar
• Hands-on experience building RAG architectures using vector databases such as Chroma, Pinecone, Weaviate, or similar
• Experience implementing observability for LLM systems using LangSmith, Langfuse, or equivalent platforms
• Strong understanding of AI security concepts including prompt injection prevention and guardrails
• Advanced proficiency in Python and backend development using FastAPI
• Good understanding of Git, Docker, and CI/CD workflows

Preferred Qualifications

• Experience with Kubernetes and cloud-native AI deployments
• Familiarity with model fine-tuning and evaluation pipelines
• Experience working with enterprise-scale AI products
• Knowledge of distributed systems and scalable backend architectures
• Experience with performance optimization and inference acceleration techniques
• Experience with MCP (Model Context Protocol) integrations and ecosystem tooling
• Hands-on experience with fine-tuning techniques such as LoRA and QLoRA
• Experience deploying AI/ML systems on cloud platforms including AWS, GCP, or Azure
• Familiarity with MLOps and experiment tracking tools such as MLflow and Weights & Biases
• Experience using RAG evaluation frameworks such as RAGAS for assessing retrieval quality and response performance