About this role
Coforge is building advanced artificial intelligence systems and enterprise-grade generative AI applications to solve complex business problems. The engineering team focuses on delivering end-to-end AI solutions that integrate large language models, retrieval-augmented generation architectures, and autonomous agents into production environments.
As a Senior AI Engineer, the person in this role will design system architectures, build scalable data integrations, and deploy reliable machine learning pipelines using Python and modern orchestration frameworks. The position exists to lead technical decision-making and ensure high reliability across production AI systems. A successful candidate will combine deep technical expertise in generative AI with strong autonomy and the ability to navigate ambiguous enterprise requirements.
What you will do
- Design and lead end-to-end artificial intelligence solutions while making critical architectural decisions for production deployments.
- Develop generative AI and large language model applications featuring RAG pipelines and autonomous agents using frameworks like LangChain and LlamaIndex.
- Build scalable data architectures on platforms such as Snowflake, Databricks, or Redshift.
- Manage the complete deployment lifecycle of AI systems, covering monitoring, observability, and troubleshooting.
- Establish evaluation strategies, quality metrics, and feedback loops to maintain system effectiveness.
- Partner closely with technical and business stakeholders to address high-impact challenges.
What you need
- Bring over five years of professional background in software engineering, data science, machine learning, or artificial intelligence.
- Demonstrate advanced proficiency in Python, API development, testing practices, and system design.
- Show proven capability in building applications powered by large language models, RAG, and agentic workflows.
- Have hands-on experience utilizing frameworks like LangGraph, Semantic Kernel, LangChain, or LlamaIndex.
- Possess working knowledge of large-scale data platforms including Snowflake, Databricks, Synapse, or Redshift.
- Know how to handle deployment, monitoring, troubleshooting, and risk mitigation for AI models in production.
Nice to have
- Experience designing AI evaluation metrics and feedback loops
- Background leading end-to-end enterprise solutions
- Experience mentoring other engineers
Skills and tech stack
Questions candidates ask
What is the work location and modality for this role?
The position is based in Peru and operates on a remote modality.
What kind of technical background is required?
Candidates must have at least five years of experience in software engineering, data science, machine learning, or artificial intelligence, along with advanced Python skills.
Which frameworks and tools will be used on the job?
The stack includes large language models, generative AI, RAG, AI agents, LangChain, LangGraph, LlamaIndex, Semantic Kernel, and large-scale data platforms like Snowflake or Databricks.