AI Engineer

Key Technical Skills & Usage Examples · Programming (Python): Essential for writing logic, connecting APIs, and building end-to-end workflows. · Frameworks (LangChain, AutoGen, CrewAI): Used for developing autonomous agent teams and multi-agent orchestration. · Prompt Engineering & Instruction Design: Creating structured prompts to improve task success rates by up to 35%. · Planning & Reasoning: Designing agents that break down complex goals into actionable sub-tasks. · Tool Use & API Orchestration: Connecting AI models to external tools (databases, browsers, calculators) to act upon data, increasing success by 46%. · Vector Databases & RAG: Implementing retrieval-augmented generation for memory and knowledge management. · Evaluation & Testing: Testing agent reliability, accuracy, and monitoring for hallucination Key Responsibilities · Design, develop, and maintain scalable AI/ML applications, with a strong focus on Python-based systems · Architect, build, and deploy production ML systems including model serving, evaluation, monitoring, and data pipelines · Develop and implement solutions using Large Language Models (LLMs), including prompt engineering, fine-tuning, and RAG-based applications · Integrate LLM APIs and build intelligent applications using vector databases, tool-based agents, and function calling · Collaborate with cross-functional teams to translate business requirements into scalable AI solutions · Ensure performance, scalability, and reliability of deployed AI systems · Continuously evaluate and adopt emerging AI/ML technologies and best practices Required Skills & Qualifications: · 5+ years of software development experience in one or more languages: Python (preferred), C/C++, Go, or Java · 3+ years of experience designing, building, and deploying production ML systems · Hands-on experience with LLMs including API integration, prompt engineering, fine-tuning, and RAG architectures · Familiarity with leading LLMs such as OpenAI, Gemini, Llama, Qwen, and Claude · Strong understanding of machine learning concepts, applied statistics, algorithms, and data structures · Experience building data pipelines and handling large-scale datasets · Strong problem-solving skills, ownership mindset, and ability to work in a fast-paced environment · Excellent communication skills with the ability to explain complex concepts clearly Preferred Qualifications: · Experience working with AWS cloud services (ECS/EKS, Lambda, S3, DynamoDB, Redshift, SageMaker) · Knowledge of containerization and orchestration (Docker, Kubernetes) · Experience with workflow orchestration (Step Functions) · Familiarity with Infrastructure as Code tools such as Terraform or CloudFormation