AI / Data Engineer

Job Summary:
We are looking for an AI / Data Engineer with strong Python programming skills and hands-on experience in LLMs, document processing, and data pipelines. The candidate will develop AI-powered capabilities for document extraction, classification, summarization, and workflow automation within an enterprise platform.
Key Responsibilities
Develop AI/LLM-based solutions for document classification, metadata extraction, and structured information extraction.
Build Python-based data pipelines for document ingestion, transformation, validation, and processing.
Implement AI-assisted document drafting and summaries of missing items, workflow blockers, and exceptions.
Integrate AI services with backend applications using REST APIs.
Implement output validation, error handling, testing, and human-review workflows for uncertain results.
Collaborate with backend, QA, and DevOps teams to deploy and maintain production-ready solutions.
Experience Range
1 - 3 years
Job Code
KL-BTBRGQ7S
Educational Qualifications
B.Tech/B.E
Job Responsibilities:
Required Skills
Strong Python programming and SQL skills.
Hands-on experience with LLM APIs and prompt engineering.
Experience with PDF parsing, OCR, document processing, or information extraction.
Knowledge of REST APIs, JSON, data validation, and ETL pipelines.
Familiarity with Pandas, Pydantic, LangChain, or similar frameworks.
Experience with Git, unit testing, debugging, and production code development.
Preferred Skills
Exposure to AWS, Azure, or other cloud-based AI services.
Experience building AI solutions for enterprise workflows or document-heavy business processes.
Skills Required
PythonLLM APIsAI/LLM-based solutionsREST APIsETL pipelinesPDF parsing, OCRAWS, Azure, or other cloud-based AI servicesPyspark
Company Description Mantra Labs is a global technology leader specializing in Digital, Data, AI, and Engineering, helping rapidly evolving enterprises drive transformational growth. The company delivers best-in-class digital product engineering, technology transformation, and AI-driven solutions to Fortune 500 clients across BFSI, healthcare, and consumer internet sectors. With over 200 successful projects, Mantra Labs focuses on optimizing digital infrastructure, improving decision-making, and simplifying customer journeys for scalable business impact. As a CMMI Level 3 and ISO 27001:2013 certified organization, and a partner of AWS, Microsoft Azure, Google Cloud, Nvidia, IBM Watson, MongoDB, Rakuten, and Katalon, it provides tailored, future-ready solutions to tackle complex business challenges. Key clients include AbbVie Pharmaceuticals, SAAB, PACE Industries, American Auto Club, Change Healthcare, and leading insurance and health brands across India and APAC.
Role Description This is a full-time, on-site AI / Data Engineer role based in Bengaluru South. The AI / Data Engineer will design, build, and maintain scalable data pipelines and platforms that support advanced analytics and AI-driven solutions for enterprise clients. Responsibilities include developing and optimizing ETL workflows, implementing data models and data warehouses, and ensuring data quality, reliability, and performance across multiple sources and environments. The role involves close collaboration with data scientists, product teams, and software engineers to operationalize machine learning models, integrate data services into applications, and support real-time and batch analytics use cases. The AI / Data Engineer will also contribute to architecture decisions, documentation, and continuous improvement of data engineering best practices and standards.
Qualifications
Candidates should possess strong skills in Data Engineering and Extract Transform Load (ETL) processes for building robust data pipelines.
Candidates should possess skills in Data Modeling and Data Warehousing to design scalable, well-structured analytical data stores.
Candidates should possess skills in Data Analytics to support reporting, dashboards, and insight generation from large datasets.
Experience with cloud data platforms and services (e.g., AWS, Azure, Google Cloud) and distributed data processing frameworks (e.g., Spark, Kafka) is beneficial.
Proficiency in programming languages commonly used for data engineering (such as Python, SQL, or Scala) and version control tools is preferred.
Understanding of machine learning workflows, model deployment, and MLOps practices is an advantage.
Bachelor’s or Master’s degree in Computer Science, Data Engineering, Information Technology, or a related field, or equivalent practical experience.
Ability to work collaboratively in cross-functional teams, communicate technical concepts clearly, and solve complex data challenges in a fast-paced environment

Work arrangement
No