Consultant AI Engineer
We are looking for a senior handson Consultant AI Engineer to design build and harden productiongrade Generative AI and Agentic AI solutions across enterprise use cases The consultant will work closely with the Lead Applied AI Engineer to build LLMpowered multiagent pipelines including RAG orchestration tool integration evaluation deployment and production pilots The role requires strong engineering rigor production delivery mindset and the ability to mentor and upskill internal engineering teams
Primary Skills Mandatory
Proven track record of shipping LLM AIML or agentic AI solutions into production preferably on AWS
Minimum 5 years of software engineering experience including at least 2 years focused on AIML LLM applications or agentic systems
Strong handson experience in Agentic AI and multiagent orchestration using production agent frameworks such as AWS Strands SDK LangGraph CrewAI or Claude Agent SDK
Experience designing and implementing ReAct tooluse loops supervisorbased orchestration DAG orchestration state management selective reexecution and humanintheloop approval gates
Handson experience with Amazon Bedrock and AWS GenAI stack including foundation models Knowledge Bases Agents S3 Lambda IAM ECSEKS or SageMaker
Experience deploying scaling and managing GenAI solutions on AWS with appropriate cost security and operational controls
Handson experience integrating AI agents with enterprise systems using Model Context Protocol MCP function calling REST APIs issue trackers source control systems or test management platforms
Strong experience building RAG and hybrid retrieval solutions using vector databases such as OpenSearch or similar platforms
Experience with embeddings semantic chunking hierarchical chunking metadata design taxonomy design hybrid retrieval reranking and retrievalfailure verification
Experience converting longcontext workflows into scalable RAGbased solutions over proprietary enterprise data
Strong understanding of transactionsafe tool integration including atomic commit rollback handling and prevention of partialwrite or inconsistentstate failures
Strong experience in prompt engineering and evaluation including prompt development versioning regression testing fewshot example curation golden sets benchmark sets and AB testing
Experience defining and tracking evaluation metrics for accuracy hallucination factual consistency cost and performance improvement across model iterations
Experience with LLMOps MLOps practices including CICD for AIenabled services monitoring observability dashboards versioning and tokencost optimization
Strong experience in Python software engineering including strict JSON schema design schema validation idempotency error handling transaction safety and clean Gitbased development workflows
Bachelors degree in Computer Science Data Science Applied Mathematics or a related technical discipline or equivalent professional experience
Secondary Skills Nice to Have
Generative AI Machine Learning Hugging Face or equivalent GenAI ML certifications
Experience with containerization using Docker or Kubernetes
Experience with Infrastructure as Code using Terraform or CloudFormation
Ability to document runbooks and support knowledge transfer to internal engineering teams
Experience prototyping in sandbox environments and promoting validated components to production AWS Bedrock environments
Familiarity with enterprise security and compliance standards for production AI deployments