Artificial Intelligence / Machine Learning Engineer

Job Description About the company: Engenious is a US-based consulting agency with a global presence. Although Engenious’ main area of expertise is mobile development, it is a home for more than 40 plus talented world-class engineers with domain experience in Web, Backend, and Test Automation. Open role: We are seeking an experienced AI/ML Engineer to join our dynamic team. Key Responsibilities Develop document-processing pipelines with ML/LLM-based extraction and agentic workflows. Build and extend Python microservices for document ingestion, classification, extraction, validation, and post-processing. Develop autonomous AI agents using tool calling, structured outputs, and advanced reasoning. Prepare evaluation datasets and define ground-truth target values for extracted data. Evaluate extraction results, analyze failures, and improve prompts, schemas, and pipeline logic. Build automated testing and regression frameworks for prompts, models, agents, and extraction workflows. Optimize AI systems for accuracy, latency, throughput, reliability, and cost. Work with asynchronous processing infrastructure using AWS services such as ECS, SQS, SNS, RDS, and S3. Use AI-assisted development tools such as Claude Code, Cursor, and similar solutions while following engineering, testing, and code-review best practices. Prototype new AI solutions in collaboration with engineering teams. Requirements At least 3 years of AI/ML experience and 6+ years of overall experience. Strong proficiency in Python. Experience building Python microservices and data-processing pipelines. Experience with OCR tools and document-processing platforms. Practical experience with LLM-based extraction, classification, reasoning, and structured outputs. Experience working with LLM providers and model families such as OpenAI, Claude, Gemini, Llama, and Grok, including multimodal models. Strong knowledge of prompt engineering, embeddings, semantic search, tool calling, and agentic workflows. Experience preparing evaluation datasets and defining expected target values. Understanding of evaluation metrics such as accuracy, precision, recall, F1 score, and completeness with AI safety guardrails, privacy controls, and prompt-injection protection. Experience with AWS services, particularly ECS, SQS, SNS, RDS, S3, OpenSearch, and CloudWatch. Experience with Docker, message queues, retry mechanisms, and distributed processing. Experience with data-processing libraries such as Pandas and NumPy. Practical experience with AI-assisted development tools such as Claude Code or Cursor. Prototyping, R&D, or hackathon experience. English proficiency at B2 level or higher. Nice to Have Experience with Promptfoo, DeepEval, LangTest, Ragas, or similar evaluation tools. Publications or contributions to open-source AI/ML projects. Our benefits: Flexible & remote job Paid vacation and sick leave Development opportunities in any IT direction Fun and friendly team Personal professional growth Up to 100% reimbursement of participation in core courses and conferences Send us your CV and take a new step in your professional career!