Position : AI/ML Developer (GenAI/LLM, Python)

Overall/Total Experience : 3 - 7 years

Location : Hyderabad

Working Days : 5 Days from Office

Notice Period Requirement : Immediate Joiners/Serving Notice Period Only

US Working Hours : 9.30PM to 6.30AM IST

Roles & Responsibilities :

- Design, build, and maintain AI/ML-powered applications in Python.

- Develop LLM-based features such as document understanding, summarisation, extraction, and conversational assistants for insurance workflows.

- Build and improve Retrieval-Augmented Generation (RAG) pipelines, including data ingestion, chunking, embeddings, vector search, and prompt design.

- Deploy, monitor, and scale models and AI services on AWS.

- Build and integrate REST APIs that expose AI capabilities to products and client systems.

- Evaluate model and LLM outputs for accuracy, relevance, latency, and cost, and improve them over time.

- Work with relational, NoSQL, and vector databases.

- Read existing code and make improvements independently with light guidance.

- Debug and fix issues across the application and AI stack.

- Follow good practices for version control, testing, and documentation.

Candidate Requirements :

- Must have 3+ years of hands-on software development experience with at least the recent 1+ years on AI/ML or LLM-based projects.

- Must have strong working knowledge of Python.

- Must have hands-on experience with LLM APIs or platforms (OpenAI, Anthropic, Amazon Bedrock, Azure OpenAI, or open-source models like Llama, Mistral).

- Must have practical experience building RAG applications using frameworks such as LangChain, LlamaIndex, or similar (data ingestion, chunking, embeddings, vector search, prompt design).

- Must have familiarity with embeddings and vector databases such as Pinecone, FAISS, Chroma, pgvector, Weaviate, or OpenSearch.

- Must have understanding of prompt engineering and ways to evaluate LLM outputs.

- Must have experience deploying models or AI services to production (FastAPI/Flask, Docker, AWS Lambda, ECS, or SageMaker).

- Must have working knowledge of AWS services (EC2, S3, Lambda, IAM, CloudWatch, ECS/ECR), and the ability to design, write, and consume REST APIs.

- Must have experience with databases (PostgreSQL, MySQL, or DynamoDB), Git-based version control, and comfort with Linux commands and shell scripting.

- Must have strong debugging and problem-solving skills.

- Familiarity with ML libraries such as PyTorch, TensorFlow, scikit-learn, or Hugging Face Transformers.