Responsibilities
- Design, build, and maintain backend services and APIs using Python frameworks such as FastAPI or Django.
- Implement RAG-based features and services, including document ingestion pipelines, vector indexing, and retrieval logic using modern LLM tooling.
- Build robust data ingestion, scraping, and automation workflows (web scraping, headless browsers, APIs) to integrate with third-party systems and internal tools.
- Develop and operate ETL/ELT pipelines to move, clean, and transform data across databases, file stores, and external platforms.
- Own reliability, performance, and observability of services: logging, metrics, alerting, and debugging in production.
- Collaborate closely with product and business stakeholders to translate ambiguous workflows into clear technical designs and automation logic.
- Write clean, testable code with solid unit/integration coverage, and contribute to internal libraries, tooling, and best practices documentation.
- Participate in code reviews, architectural discussions, and mentor junior engineers on Python, RAG patterns, and automation best practices.
Requirements
- 46 years of hands-on experience as a Python engineer building production systems (FastAPI, Django, or similar).
- Strong understanding of backend fundamentals: REST APIs, authentication/authorisation, async patterns, background jobs, and task queues.
- Experience with event-driven architectures (Kafka, SQS, RabbitMQ) and workflow engines (e.g., Temporal, Airflow, Prefect).
- Practical experience with at least one LLM/RAG stack (e.g., LangChain, LlamaIndex, custom vector store integrations) and working with embeddings, chunking, and retrieval.
- Solid experience with web scraping and automation: requests/HTTP clients, Selenium/Playwright or similar, rate-limiting, anti-bot handling, and resilient scraping patterns.
- Experience building data pipelines or ETLs: extracting from APIs/files/DBs, transforming/cleaning, and loading into relational or NoSQL stores.
- Hands-on experience with AWS or similar cloud platforms (e.g., Lambda, S3, API Gateway, ECS/Fargate, or equivalent).
- Strong debugging skills and comfort with distributed, asynchronous systems and eventual consistency.
- Ability to take loosely defined business workflows and design clean, maintainable technical solutions.
- Strong communication skills and a habit of documenting decisions, APIs, and workflows.
Nice To Have
- Experience with vector databases (e.g., Pinecone, Weaviate, Qdrant, OpenSearch vector, etc.) and search tuning.
- Exposure to building internal tools or low-code-like automation platforms for operations or support teams.
- Prior experience integrating with ERP/CRM/marketplace or other enterprise/legacy systems.
- Understanding of cloud security, IAM, and secret management best practices.
Skills:- Process automation, RPA, Python, AWS Lambda, AWS Simple Queuing Service (SQS), Apache Kafka, Selenium, uipath, Amazon S3, Blueprism, langchain and playwright
