Artificial Intelligence Engineer

Job Title: AI Engineer AWS & Generative AI

Experience Level: 2 to 5 years (with at least 2 years of hands-on experience in Generative AI solutions on AWS)

Role Overview

We are looking for a hands-on AI Engineer with strong experience in building production-ready Generative AI solutions on AWS. The ideal candidate will have prior experience implementing RAG (Retrieval-Augmented Generation) solutions, working with agentic frameworks, and deploying AI/ML workloads using AWS-native services. This is a core engineering role that requires deep technical expertise, problem-solving skills, and the ability to build end-to-end AI solutions in real-world enterprise environments.

You will work closely with architects, data engineers, and product teams to translate business requirements into scalable AI solutions, with a focus on autonomous agents and production-grade generative AI systems.

Key Responsibilities

• Design and implement RAG-based architectures leveraging AWS services, vector databases, and LLMs with advanced retrieval strategies (hybrid search, reranking, document processing pipelines).
• Develop and deploy agentic workflows using frameworks such as CrewAI, LangGraph, Bedrock Strands Agents, or similar, including multi-agent orchestration and tool-calling implementations.
• Build agent memory systems (short-term, long-term, semantic) and implement context management strategies for complex workflows.
• Build, train, and deploy models on AWS Bedrock, SageMaker, AWS Transcribe/Translate/Comprehend, Kendra, and related services.
• Implement guardrails, content filters, and safety mechanisms for LLM outputs including PII detection and bias mitigation.
• Design and maintain evaluation frameworks for agent performance, accuracy, and reliability using metrics like RAGAS and human-in-the-loop evaluation.
• Build observability and monitoring for agentic workflows including tracing, logging, and debugging using tools like CloudWatch, X-Ray, LangSmith, or similar.
• Develop prompt engineering strategies and prompt management systems for production environments.
• Work closely with architects and engineering teams to integrate AI capabilities into existing enterprise systems using APIs, event-driven patterns, and data pipelines.
• Develop Python-based pipelines and APIs for AI workflows and automation, including streaming responses and real-time inference.
• Optimize inference, cost, and performance of deployed models on AWS through A/B testing and continuous improvement.
• Evaluate new LLMs, embeddings, and agent frameworks, and recommend best-fit approaches for projects.
• Collaborate with cross-functional teams and stakeholders to design MVPs, prototypes, and production-scale solutions from business requirements.

Required Skills & Experience

• Hands-on AWS AI/ML stack: Bedrock, SageMaker, Transcribe, Translate, Comprehend, Kendra, Lambda, API Gateway, Step Functions, EventBridge.
• RAG implementation experience (at least one production project) using embeddings, vector databases, and hybrid search strategies.
• Agentic AI frameworks: CrewAI, LangGraph, Bedrock Strands Agents, or equivalent with experience in tool-calling/function-calling and multi-agent orchestration.
• Experience with agent orchestration patterns (ReAct, Plan-and-Execute, reflection) and autonomous agent design.
• Strong prompt engineering skills and experience with prompt management at scale.
• Knowledge of LLM evaluation metrics and agent performance monitoring.
• Strong Python programming skills with experience in ML/AI libraries (LangChain, HuggingFace, PyTorch/TensorFlow optional but good to have).
• Experience with vector/semantic databases such as OpenSearch, Weaviate, Pinecone, or equivalent.
• Understanding of observability tools for AI workflows (CloudWatch, X-Ray, LangSmith, Phoenix, or similar).
• Familiarity with enterprise integration patterns (APIs, data pipelines, event-driven architectures, security, observability).
• Experience with document processing pipelines for unstructured data (PDFs, images, etc.).
• Strong problem-solving and debugging skills in production environments.

Preferred (Good to Have)

• Exposure to MLOps practices (CI/CD for ML, model monitoring, retraining pipelines).
• Experience with fine-tuning or RLHF on SageMaker or Bedrock.
• Familiarity with data processing tools (Glue, Athena, Redshift, or similar).
• Understanding of cost optimization and scaling on AWS including inference optimization.
• Knowledge of governance frameworks for AI (model cards, bias detection, responsible AI practices).
• Prior experience in multi-tenant SaaS or enterprise platforms.
• Experience with context window management and advanced chunking strategies.
• Familiarity with reranking models and retrieval optimization techniques.

Qualifications

• Bachelors/Masters degree in Computer Science, Engineering, or related field (or equivalent practical experience).
• 2+ years of hands-on AI/ML development with Generative AI solutions.
• Demonstrated ability to translate business requirements into technical AI solution