Sr Associate

Chryselys; Hyderabad; On-site; INR 900,000 - 1,300,000; Full time

Job summary

Chryselys in Hyderabad is seeking a Backend Developer to build scalable, secure services for GenAI-enabled applications. You will work on backend APIs, data ingestion, web scraping workflows, and metadata management to empower AI-powered products.

Ideal candidates have 3–6 years of backend development experience with Python/Node/Java, RESTful APIs, and familiarity with GenAI patterns, data pipelines, and cloud deployments. Join a fast-paced cross-functional team shaping GenAI delivery.

Qualifications

• Hands-on backend development with a server-side stack (Python/Node/Java).
• Experience designing RESTful APIs, microservices, and integration layers.
• Familiarity with GenAI patterns like embeddings, retrieval, and LLM APIs.
• Proficient in web scraping frameworks and data extraction workflows.

Responsibilities

• Design, develop, test, and maintain backend services and APIs.
• Build data ingestion pipelines and robust web scraping solutions.
• Handle unstructured content conversion for search and analytics.
• Implement metadata extraction, tagging, and indexing strategies.
• Integrate with LLM APIs, vector stores, and GenAI frameworks.
• Collaborate with product, data science, QA, and stakeholders.
• Ensure security, performance, observability, and reliable deployments.

Skills

Backend development

RESTful APIs

GenAI patterns

Web scraping

Unstructured data

Metadata models

Relational/NoSQL DBs

Cloud & CI/CD

Clean code

Problem solving

Education

Bachelor/Master in CS/IT/Engineering

Tools

FastAPI

Django/Flask

Express.js

Spring Boot

Job description

Role Summary

The Chryselys PACE team is looking for a Backend Developer to build scalable, secure, and production-ready services for GenAI-enabled applications. The role will focus on backend API development, data ingestion pipelines, web scraping workflows, unstructured data processing, metadata management, and integration with AI/LLM-based systems. The ideal candidate should be comfortable working across application engineering, data engineering, and GenAI solution delivery.

Key Responsibilities

• Design, develop, test, and maintain backend services, APIs, and integration layers for GenAI-driven products and internal platforms.
• Build robust data ingestion pipelines to collect, parse, transform, validate, and prepare structured and unstructured data for downstream AI workflows.
• Develop and maintain reliable web scraping solutions, including scheduling, error handling, data quality checks, rate limiting, and compliance-aware extraction patterns.
• Work with unstructured content such as PDFs, web pages, documents, emails, transcripts, and knowledge repositories, converting them into usable formats for search, analytics, and AI applications.
• Implement metadata extraction, enrichment, tagging, lineage tracking, and indexing strategies to improve discoverability, traceability, and retrieval quality.
• Integrate backend systems with LLM APIs, embedding models, vector databases, retrieval pipelines, and GenAI orchestration frameworks where required.
• Collaborate with product managers, data scientists, GenAI engineers, QA teams, and business stakeholders to translate requirements into scalable technical solutions.
• Ensure backend solutions meet standards for security, performance, observability, maintainability, and reliability.
• Participate in code reviews, technical design discussions, troubleshooting, documentation, and continuous improvement of engineering practices.

Required Skills and Experience

• Strong backend development experience using Python, Node.js, Java, or a comparable server-side technology stack.
• Hands-on experience designing RESTful APIs, microservices, background jobs, and integration services.
• Experience with GenAI application patterns such as prompt-based workflows, Retrieval-Augmented Generation, embeddings, semantic search, vector stores, or LLM API integration.
• Practical experience with web scraping frameworks and libraries such as BeautifulSoup, Scrapy, Playwright, Selenium, Requests, or equivalent tools.
• Strong understanding of unstructured data extraction, parsing, chunking, normalization, deduplication, validation, and data quality handling.
• Experience managing metadata models, taxonomies, tagging structures, document attributes, source provenance, and indexing strategies.
• Good knowledge of relational and/or NoSQL databases such as PostgreSQL, SQL Server, MongoDB, Elasticsearch, or similar platforms.
• Familiarity with cloud platforms, containerization, CI/CD pipelines, logging, monitoring, and secure deployment practices.
• Ability to write clean, modular, testable, and well-documented code.
• Strong problem-solving skills and ability to work in a fast-paced, cross-functional delivery environment.

Preferred Qualifications

• Experience with frameworks such as FastAPI, Django, Flask, Express.js, Spring Boot, or similar backend frameworks.
• Exposure to LangChain, LlamaIndex, Semantic Kernel, Azure OpenAI, OpenAI APIs, AWS Bedrock, Google Vertex AI, or similar GenAI platforms.
• Experience with vector databases or search platforms such as Azure AI Search, Pinecone, Weaviate, ChromaDB, FAISS, Elasticsearch, or OpenSearch.
• Knowledge of data privacy, responsible AI, secure handling of scraped/public data, and compliance-aware ingestion practices.
• Experience with document intelligence, knowledge management, enterprise search, content extraction, or pharma/life sciences data platforms is a plus.
• Familiarity with agile delivery, Jira/Azure DevOps, Git-based workflows, and production support processes.

Education and Experience

Bachelor s or Master s degree in Computer Science, Information Technology, Engineering, Data Science, or a related field. Typically suited for candidates with 3-6 years of backend development experience, including hands-on exposure to GenAI projects, web scraping, unstructured data pipelines, and metadata-driven data platforms.