Ai Engineer – Llms & Agentive Ai, Palakkad

Job Title:

AI Engineer – LLMs & Agentive AI (Amazon Bedrock Focus)

Job Summary:

We are seeking a skilled and forward-thinking AI Engineer to join our team in building intelligent, context-aware AI applications using LLMs, Amazon Bedrock AI Agents, and agentic architectures. You will design, develop, and deploy multi-agent systems, autonomous workflows, and intelligent task handlers leveraging foundation models (FMs) and orchestration tools to deliver scalable and secure solutions.

Key Responsibilities:

LLM Development & Integration

Design, fine-tune, and integrate large language models (LLMs) using platforms such as Amazon Bedrock, Open AI, or Anthropic.

Leverage foundation models (Jurassic, Claude, Titan, etc.) via Bedrock to build secure, enterprise-grade generative AI applications.

Apply prompt engineering techniques and prompt chaining for dynamic, multi-turn interactions.

AI Agent Development

Build agentic AI systems using Amazon Bedrock Agents or similar frameworks (Lang Chain, Re Act, Auto GPT, Crew AI, etc.).

Define tools, actions, and memory systems for agents to perform tasks autonomously based on goals, context, and user feedback.

Implement custom logic for orchestration, context management, and multi-agent collaboration.

System Integration & Infrastructure

Develop scalable, production-grade pipelines for serving AI agents via APIs or UI-based interfaces.

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

Use AWS services (Lambda, S3, API Gateway, Dynamo DB, Cloud Watch) to build secure and scalable agent pipelines.

Required Skills & Experience:

4–7 years in AI/ML engineering, with deep understanding of LLMs and transformer-based architectures.

Hands-on experience with Amazon Bedrock, including working with FMs and Bedrock Agents.

Proficiency in Python and experience with LLM frameworks such as Lang Chain, Llama Index, or Semantic Kernel.

Strong understanding of prompt engineering, RAG pipelines, and tool/function calling for agents.

Familiarity with deploying applications on AWS cloud infrastructure using serverless or container-based patterns.