We are looking for a skilled Generative AI Developer with hands-on experience in building and deploying AI-powered solutions across cloud platforms. The ideal candidate will have strong expertise in LLMs, OCR, custom ML models, vector databases, and AI agent frameworks, along with solid software development experience following SDLC best practices.

Key Responsibilities :

- Design, develop, and deploy Generative AI and NLP-based solutions leveraging frameworks like LangChain, Semantic Kernel, and AutoGen

- Implement and optimize custom ML models for tasks such as document understanding, OCR, and data extraction

- Integrate LLMs and AI services using AWS Bedrock, Azure OpenAI, and SageMaker AI Foundry

- Work with vector databases (e.g., Pinecone, FAISS, Chroma, Weaviate) for retrieval-augmented generation (RAG) and semantic search

- Utilize AWS services (SQS, SNS, S3, Lambda) and Azure services (Service Bus, Event Grid, Functions) for building event-driven architectures

- Work with databases including PostgreSQL, DynamoDB, CosmosDB, and other relational/NoSQL solutions

- Leverage Databricks for large-scale data processing and ML workflows

- Collaborate with backend teams to design robust AI-driven microservices and APIs

- Ensure scalable and production-grade ML pipelines, adhering to CI/CD and MLOps practices

- Conduct model evaluations, fine-tuning, and prompt engineering for improved performance

- Stay updated with emerging trends in transformer architectures, multimodal AI, and generative agent frameworks

Required Skills & Experience :

- 4- 6 years of professional experience in AI/ML software development

- Strong proficiency in Python, with experience using frameworks like PyTorch, TensorFlow, or Hugging Face Transformers

- Proven experience with OCR/document parsing tools (e.g., Tesseract, Azure Form Recognizer, AWS Textract)

- Hands-on experience with LLM orchestration frameworks LangChain, Semantic Kernel, AutoGen, or similar

- Expertise in backend development (FastAPI, Flask, Node.js, etc.) and integration of AI services into applications

- Strong understanding of SDLC, version control (Git), and cloud deployment best practices

- Working knowledge of AWS (Bedrock, SageMaker, SQS, SNS, Lambda, S3) and/or Azure AI stack (OpenAI, Cognitive Services, Service Bus, Event Grid, Functions)

- Experience with Databricks for data engineering and ML pipelines

- Proficiency with databases such as PostgreSQL, DynamoDB, CosmosDB, and other SQL/NoSQL solutions

- Familiarity with vector databases, prompt engineering, and AI agent design