Job Title: Python GenAI Engineer
Experience: 58 Years
Location: Pune
Notice Period: Immediate Joiner Only
Position Overview
We are looking for a highly skilled Senior Generative AI / Backend Engineer with strong experience in building AI-powered applications and scalable backend systems. The ideal candidate will have hands-on expertise in LLMs, Retrieval-Augmented Generation (RAG), prompt engineering, and Python-based backend development, with the ability to deliver production-ready AI solutions.
Key Responsibilities
Generative AI Development
- Design, develop, and deploy generative AI solutions using frameworks such as LangChain and LlamaIndex.
- Apply advanced prompt engineering techniques to optimize LLM responses across multiple use cases.
- Work with advanced LLM features including prompt optimization, hyperparameter tuning, and response caching.
- Implement Retrieval-Augmented Generation (RAG) workflows by integrating vector databases such as Pinecone, Weaviate, Supabase, or PGVector.
- Develop solutions leveraging embeddings and similarity search for intelligent and personalized query resolution.
- Process and analyze multimodal data, including text, images, and video for AI-driven applications.
- Integrate observability and monitoring tools to track LLM performance, reliability, and quality.
Backend Engineering
- Build and maintain scalable, secure backend services using Python frameworks such as FastAPI, Django, or Flask.
- Design and implement RESTful APIs for seamless system integration.
- Optimize and manage relational databases (PostgreSQL, MySQL) and vector databases for AI workflows.
- Implement asynchronous programming patterns and follow clean coding best practices.
- Integrate third-party SDKs and APIs to support external system interoperability.
- Develop backend pipelines for multimodal data processing (text, image, and video).
- Manage background and scheduled tasks using Celery, cron jobs, or job queues.
- Use Docker for containerization and reproducible deployments.
- Ensure backend systems are secure, scalable, and production-ready.
Qualifications
Essential Skills
- Strong proficiency in Python and backend frameworks (FastAPI, Django, Flask).
- Hands-on experience with Generative AI frameworks such as LangChain, LlamaIndex, and RAG architectures.
- Strong understanding of LLMs, embeddings, and similarity search techniques.
- Experience with relational databases (PostgreSQL, MySQL) and vector databases (Pinecone, Weaviate, Supabase, PGVector).
- Experience deploying AI solutions to production using Docker.
- Strong skills in testing, debugging, and performance optimization (Pytest, unit/integration testing).
- Solid understanding of asynchronous programming and concurrent task handling.
Preferred Skills
- Experience with cloud platforms such as AWS, GCP, or Azure.
- Basic understanding of frontend technologies (HTML, CSS, JavaScript; Angular or React is a plus).
- Experience with observability and monitoring tools for real-time LLM evaluation.
- Awareness of emerging trends in generative AI, multimodal AI, and agent-based workflows.
- Knowledge of secure coding practices and backend system hardening.
- Relevant certifications in AI, Machine Learning, or Cloud technologies are a plus.
