Responsibilities :
- Design, build, and maintain our AI-driven knowledge graph creation pipeline
- Integrate third-party APIs for web scraping (e.g., Browserless), search (e.g., Tavily), and multimedia processing
- Develop and refine sophisticated prompts for Large Language Models (Amazon Bedrock, Claude) to perform high-accuracy data extraction from unstructured text and video transcripts
- Build and manage the backend data workflow using Python and Django, populating a PostgreSQL database
- Implement an agentic AI system that translates natural language user queries into structured database lookups via the Django ORM
- Develop data validation, cleaning, and entity deduplication logic to ensure knowledge graph integrity
- Optimize the end-to-end pipeline for performance, scalability, and cost-effectiveness
Required Technical Skills :
4+ years of software development experience with strong Python proficiencyProven experience working with major LLM APIs (Amazon Bedrock, OpenAI, Google Gemini)Expertise in prompt engineering for complex data extraction and agentic tasksHands-on experience with web scraping tools or services (e.g., Beautiful Soup, Scrapy, Browserless, Apify)Strong experience with backend frameworks, preferably DjangoProficiency with relational databases (PostgreSQL) and ORMsExperience integrating various REST APIsProficiency with version control (Git)Preferred Skills :
Experience with agentic frameworks like LangChain or LangGraphFamiliarity with cloud services, particularly AWS (S3, Lambda, RDS, Transcribe)Knowledge of workflow automation tools (e.g., n8n, Airflow)Understanding of graph databases (Amazon Neptune, Neo4j) and query languages (Gremlin, Cypher)Experience with multimedia processing libraries (e.g., ffmpeg)CI / CD for AI / ML systemsFamiliarity with vector databases and semantic search conceptsTechnical Requirements :
Deep understanding of Retrieval-Augmented Generation (RAG) architectureExperience building secure Text-to-SQL or Text-to-ORM systemsProficiency in processing both unstructured (text, transcripts) and structured (database) dataStrong knowledge of data structures, algorithms, and system design principlesUnderstanding of the trade-offs between different data storage solutions (SQL vs. Graph vs. Vector)Qualifications :
Bachelor's in Computer Science, AI, Data Science, or a related field2+ years of relevant software engineering experience, with a significant focus on AI solutionsStrong analytical and problem-solving abilities, especially with messy, real-world dataExcellent communication skills to articulate complex technical conceptsExperience working in Agile / Scrum environmentsBenefits :
Competitive salary and benefits packageOpportunity to work on challenging projects using cutting-edge technologiesProfessional development opportunitiesFlexible work arrangementsCollaborative and innovative work environmentHealth insurance and other benefitsRegular team events and activitiesContact us :
Send us your resume with your preferred position to below address
careers@gumo.co.in