AI/ML Full Stack Engineer

We are seeking a Senior AI/ML Full Stack Engineer to design and deliver production-grade intelligent applications powered by modern AI/ML and large language model (LLM) technologies. You will play a key role in building scalable systems that leverage retrieval-augmented generation (RAG), conversational AI, and cloud-native architectures.

This role is ideal for engineers with strong software engineering fundamentals and hands-on experience deploying AI/ML solutions into real-world production environments., * 10+ years of experience in software development (Java or Python)

• 2+ years of hands-on experience building AI/ML applications in production environments
• Strong experience building and consuming APIs (REST or GraphQL)
• Experience with CI/CD pipelines and modern development workflows
• Experience working with microservices and event-driven architectures

Preferred Qualifications

• Deep expertise in RAG (Retrieval-Augmented Generation) architectures, including:
• Chunking strategies
• Embedding models
• Vector databases (Pinecone, OpenSearch, pgvector, FAISS)
• Experience with AI orchestration frameworks such as:
• LangChain
• LlamaIndex
• Semantic Kernel
• CrewAI
• Hands-on experience with:
• AWS Bedrock and foundation models (e.g., Anthropic Claude)
• Model invocation APIs
• Strong proficiency in prompt engineering, including:
• System prompts, few-shot learning
• Chain-of-thought reasoning
• Tool usage and structured outputs
• Experience building conversational AI systems:
• Chatbots (text-based)
• Voicebots (speech-to-text, text-to-speech integration)
• Expertise with AWS cloud services:
• Lambda, Step Functions, API Gateway
• S3, DynamoDB, SQS
• Experience with:
• Containerization and orchestration (Docker, ECS, EKS)
• Infrastructure-as-code (Terraform, CloudFormation, etc.)
• Familiarity with:
• LLM evaluation frameworks and performance monitoring
• Guardrails, safety systems, and responsible AI practices