AI Engineer - Generative AI & LLMs (AWS)
Role details
Job location
Tech stack
Job description
-
Design, develop, and deploy enterprise AI solutions using LLMs, Prompt Engineering, Agentic AI frameworks, Machine Learning, and Data Science techniques
-
Build intelligent applications such as RAG systems, AI copilots, conversational assistants, agent workflows, document intelligence, and NLP applications
-
Design and optimize prompts including templates, chaining strategies, structured outputs, and response optimization
-
Develop and maintain data pipelines for structured and unstructured data supporting training, inference, analytics, and evaluation
-
Implement retrieval pipelines, embeddings, vector search, tool calling, memory strategies, and orchestration for LLM applications
-
Fine-tune, evaluate, optimize, and monitor AI/ML and LLM systems for performance, scalability, and cost efficiency
-
Collaborate with stakeholders to translate business requirements into scalable AI solutions
-
Build and manage AI infrastructure on AWS (e.g., S3, Lambda, EKS/ECS, API Gateway, IAM, CloudWatch, RDS, DynamoDB, OpenSearch, Bedrock)
-
Provision infrastructure using Terraform/Scalr for secure, repeatable deployments
-
Implement observability, monitoring, evaluation, feedback loops, and guardrails for AI systems
-
Ensure solutions meet enterprise standards for security, compliance, and resiliency
-
Lead technical design discussions, code reviews, and engineering best practices
-
Support MLOps/LLMOps practices including CI/CD, versioning, testing, deployment, and incident response
-
Communicate technical findings and risks to stakeholders and leadership
-
Mentor junior engineers and contribute to reusable frameworks and standards
Requirements
-
Bachelor's degree in Computer Science, Engineering, Data Science, Artificial Intelligence, or related field
-
1+ years of experience in Python and software development for AI/ML, data engineering, or cloud applications
-
1+ years of experience in Machine Learning / Data Science including model development and deployment
-
1+ years of experience in LLMs / Generative AI including prompt engineering, RAG, embeddings, and evaluation frameworks
-
Strong experience in Prompt Engineering (design patterns, chaining, structured outputs, prompt tuning)
-
Strong understanding of Agentic AI workflows, orchestration, memory handling, and tool usage
-
Experience with AWS for developing and deploying AI/ML solutions
-
Experience with Terraform and/or Scalr for infrastructure provisioning
-
Experience with APIs, microservices, and containerized environments
-
Experience with SQL, NoSQL, vector databases, and data integration
-
Strong knowledge of software engineering fundamentals (version control, CI/CD, testing, secure coding)
-
Experience presenting technical concepts to stakeholders
-
Strong analytical, problem-solving, and collaboration skills