Website:
tya.co.in
Job details:
Location
Bengaluru, Karnataka, India
About the Role
We are looking for a highly capable Python Backend / AI Engineer to join our engineering team and build intelligent, production-grade AI systems focused on document understanding, extraction workflows, and backend automation. This role requires strong hands-on expertise in Python backend development, LLM integrations, cloud-native services, data processing pipelines, and scalable API architectures. You will work on systems that process high-volume business documents, power AI-driven prediction workflows, and integrate modern generative AI capabilities into enterprise platforms.
What You Will Do
- Design and develop scalable Python services for intelligent document extraction, validation, enrichment, and prediction workflows.
- Build and optimize production-grade pipelines for PDFs, images, and Excel-based business documents.
- Integrate and enhance Google Gemini and other LLM APIs for structured extraction, reasoning, and workflow automation.
- Develop robust prompt engineering strategies, schema-driven parsing, retry mechanisms, fallback handling, and AI response validation systems.
- Build resilient backend APIs and asynchronous processing systems using FastAPI / Flask.
- Develop reusable internal frameworks for extraction orchestration and workflow automation.
- Work on document understanding and image-processing pipelines using PyMuPDF, pdf2image, Pillow, OpenCV, and related tooling.
- Build semantic similarity and intelligent matching systems using sentence-transformers and rapidfuzz.
- Design highly maintainable backend architectures with strong logging, observability, testing, and operational reliability.
- Work on AWS-based deployments and serverless architectures using Lambda and boto3.
Mandatory RequirementsExperience:
- Experience: 3–4 years of professional experience in Backend Engineering, AI Engineering, or ML-focused software development.
- Python Engineering: Advanced proficiency in Python 3.x with strong understanding of modular architecture, APIs, typing, logging, exception handling, concurrency, and performance optimization.
- AI / LLM Experience: Hands-on experience with Google Gemini / google-generativeai, structured outputs, prompt engineering, parsing, retries, guardrails, and fallback handling.
- Document Processing: Strong experience with PyMuPDF, pdf2image, Pillow, openpyxl, and large-scale document processing workflows.
- Backend APIs: FastAPI or Flask, REST architecture, request validation, structured response models.
- AWS: Lambda, boto3, deployment packaging, monitoring, runtime optimization, and serverless architecture.
- Databases: MySQL, SQLAlchemy, MongoDB, pymongo, query optimization, and schema design.
- ML Stack: pandas, numpy, scikit-learn, joblib, semantic similarity systems, and prediction workflows.
- Engineering Practices: Git, code reviews, debugging, and working within large production codebases.
Strongly Preferred
sentence-transformers, rapidfuzz, OpenCV, ultralytics, Google Cloud Document AI / Vision, SageMaker, jsonschema, structlog, vector search systems, and finance/invoice workflow exposure.
Education
Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience.
Tech Stack
- Backend & APIs: Python, FastAPI, Flask, Pydantic
- AI & ML: Google Gemini, OpenAI APIs, scikit-learn, sentence-transformers
- Document Processing: PyMuPDF, pdf2image, Pillow, openpyxl
- Cloud & Infrastructure: AWS Lambda, boto3
- Databases: MySQL, MongoDB
- Additional Libraries: pandas, numpy, rapidfuzz, OpenCV
What We’re Looking For
• Strong ownership mindset
• Ability to independently drive complex backend features
• High engineering standards and attention to detail
• Strong debugging and problem-solving capability
• Passion for building reliable AI-powered systems
• Ability to thrive in fast-paced engineering environments
• Strong communication and collaboration skills
Click on Apply to know more.