AI Engineer

Responsibilities

• Design and implement production-grade LLM applications, managing the full stack from data ingestion and vector database integration to prompt engineering, fine-tuning, and model evaluation.
• Build and deploy sophisticated intelligent agents capable of complex reasoning, secure tool usage, and autonomous execution of multi-step business workflows.
• Own the deployment process, including self-healing systems, latency optimization, cost management, and robust performance monitoring and alerting in a large-scale enterprise environment.
• Partner closely with cross-functional teams (Legal, Finance, HR, etc.) to identify operational bottlenecks and translate them into efficient, code-driven AI automation.
• Implement rigorous standards for security, data privacy, and accuracy, ensuring the AI framework integrates seamlessly with existing corporate infrastructure.

Requirements

• 5+ years in Data Engineering, Software Engineering, or Data Science, with at least 2+ years of hands-on experience deploying GenAI/LLMs in a production enterprise environment.
• Deep proficiency in Python and frameworks such as LangChain, LlamaIndex, or AutoGen.
• Experience with cloud AI services (AWS Bedrock or Google Vertex AI) and vector databases (Pinecone, Weaviate, Milvus, or OpenSearch).
• Experience building agents and AI workflows.
• Proven ability to translate business pain into technical requirements.

Nice-to-Haves

• Previous experience building AI solutions for corporate functions like Finance, Legal (e.g., contract analysis), HR (e.g., policy retrieval), or Supply Chain (e.g., forecasting efficiency).
• Familiarity with automated evaluation pipelines like RAGAS, Arize, or other LLM-based evaluation metrics.
• Experience with techniques such as quantization, speculative decoding, or efficient fine-tuning (LoRA/QLoRA) to improve model performance and reduce inference costs.
• Previous experience in the autonomous vehicle, robotics, or high-tech manufacturing sectors.