Generative AI Engineer

About this role

Generative AI Engineer
Location: LATAM
Type of Contract: Full-Time
Salary Range: Market rates
Language Requirements: Professional English
Our client is seeking a skilled Generative AI Engineer with extensive experience building production-grade AI applications and scalable cloud-native solutions. You will play a key role in designing, developing, and deploying enterprise Generative AI platforms using modern LLM frameworks, AWS services, and event-driven architectures. Your work will directly impact the delivery of innovative AI-powered solutions that drive business efficiency and enhance customer outcomes.
Key Responsibilities

• Design, build, and deploy production-grade Generative AI applications using Python and modern AI frameworks.

• Develop and optimize Retrieval-Augmented Generation (RAG) pipelines utilizing LangChain, LangSmith, vector databases, prompt engineering, and LLM orchestration.

• Architect and deploy scalable cloud-native solutions on AWS using services such as Lambda, Bedrock, S3, DynamoDB, EC2, and Fargate.

• Build and maintain RESTful APIs using FastAPI, Django, Flask, or similar Python frameworks.

• Design and implement event-driven microservices using Kafka and distributed system best practices.

• Collaborate with cross-functional teams in Agile environments to deliver high-quality AI solutions while communicating effectively with technical and business stakeholders.

• Optimize application performance, reliability, and scalability across cloud infrastructure and AI workflows.

Must-Have Qualifications

• 7+ years of experience in Software Engineering, Data Engineering, AI Engineering, or a related technical field.

• Expert-level proficiency in Python development.

• Proven experience building and deploying production-grade Generative AI solutions.

• Hands-on experience with LangChain, LangSmith, Retrieval-Augmented Generation (RAG), vector databases, prompt engineering, and LLM orchestration.

• Strong experience with AWS services including Lambda, Bedrock, S3, DynamoDB, EC2, and Fargate.

• Experience developing APIs with FastAPI, Django, Flask, or similar frameworks.

• Strong knowledge of Kafka, event-driven architectures, distributed systems, microservices, relational databases, and NoSQL databases.

• Experience working in Agile development environments with excellent communication and stakeholder management skills.

Preferred Qualifications

• Experience designing and deploying multi-agent AI systems.

• Hands-on experience with Anthropic Claude, OpenAI, Gemini, Llama, or other enterprise LLMs.

• Experience with graph databases such as Neptune or Neo4j.

• Knowledge of AI security, red teaming, and LLM vulnerability assessment.

• Experience implementing AI governance, compliance, and responsible AI frameworks.

• Experience using Terraform or other Infrastructure as Code (IaC) tools.

• Experience with Apache Spark and large-scale distributed data processing.

• Industry experience supporting fraud detection, financial services, telecommunications, or public sector AI solutions.

Originally posted on Himalayas