
Generative AI Engineer
- Pune, Maharashtra
- Permanent
- Full-time
- Implement Data & Embedding Pipelines: Build, scale, and maintain the data ingestion and vector embedding pipelines that feed our RAG (Retrieval-Augmented Generation) systems, working with data from sources like Kafka and Postgres/MSSQL.
- Develop Scalable AI APIs: Construct and deploy high-performance APIs (using frameworks like FastAPI, .NET Web API, or Node.js) to serve search results and LLM-generated content to our applications.
- Integrate and Experiment: Collaborate with the Lead AI Engineer and front-end teams to integrate AI-powered features into our user interface. You will help set up and run A/B tests to measure impact.
- Ensure Observability: Instrument all services with OpenTelemetry and contribute to our LLMOps framework by pushing detailed metrics to Prometheus and Grafana, helping us monitor performance, cost, and quality.
- Hybrid Experience: 3+ years of professional experience, demonstrating a strong foundation in Python for data processing/AI tasks, PLUS proficiency in a backend language such as C# (.NET), Java, or Node.js.
- Data & Messaging: Solid experience with SQL (Postgres/MSSQL) and a strong understanding of message queue patterns using Kafka (both consumer and producer).
- Search Technology: Hands-on experience with search platforms like OpenSearch or Elasticsearch, including index management and writing complex queries.
- Engineering Fundamentals: Proficiency with Docker for containerization and core Git workflows.
- Exposure to Generative AI frameworks like LangChain or Hugging Face Transformers.
- Familiarity with vector databases and vector search concepts.
- Front-end experience with React or Next.js.
- Experience with CI/CD tools like Azure Pipelines or GitHub Actions.
- Basic understanding of Kubernetes.