Job Title: AI SRE Engineer
Key Skills: Python, Go, Agentic AI, LLMs, MCP, DevOps, Kubernetes, Docker, AI Security, Observability, RAG
Experience: 3–5 YOE
Location: San José, Costa Rica
Mode: Hybrid – 2–3 days per week on-site
We at Coforge are hiring AI SRE Engineer (#006fu00000QeELXAA3-10) with the following skill set.
Key Responsibilities
-
Design and deploy intelligent agent systems and Model Context Protocol (MCP) integrations that connect AI-powered experiences with enterprise DevOps tools such as GitHub, Jenkins, and Jira.
-
Build production-grade services in Python and Go, integrating enterprise data, APIs, and developer environments to enable secure and scalable AI-driven workflows.
-
Implement security controls, guardrails, policy enforcement, testing pipelines, and monitoring to ensure the reliability, safety, performance, and observability of AI systems.
-
Collaborate with product, research, and platform teams to deliver scalable solutions while documenting technical designs, standards, and best practices.
Required Skills & Qualifications
-
Bachelor’s or master’s degree in Computer Science, Engineering, or a related field, or equivalent experience.
-
3–5 years of relevant software engineering experience.
-
Strong programming skills in Python and Go, with experience building production-grade distributed systems.
-
Hands-on experience with LLMs, NLP, and AI frameworks such as PyTorch, TensorFlow, LangChain, or Ray.
-
Experience with DevOps tools such as GitHub, GitLab, Jenkins, Jira, ArgoCD, and Artifactory, including API integrations.
-
Knowledge of secure software development, authentication, and access control mechanisms.
-
Experience with cloud-native platforms and containerized environments using Docker and Kubernetes.
-
Strong debugging and problem-solving skills in fast-paced, iterative environments.
-
Understanding of AI security, reliability, and observability principles.
Preferred Skills:
-
Experience building MCP services or similar AI service-integration frameworks.
-
Knowledge of AI security practices, including guardrails, adversarial testing, red teaming, and policy enforcement.
-
Experience with AI evaluation frameworks for benchmarking model performance.
-
Experience building observability pipelines using Prometheus, Grafana, ELK Stack, or OpenTelemetry.
-
Familiarity with RAG, embeddings, and semantic search for context augmentation.
-
Contributions to open-source AI or DevOps projects.
Posted On: 22-10-2026
At Coforge, we hire professionals based solely on their skills and do not discriminate based on age, disability, religion, gender, sexual orientation, socioeconomic status, or nationality.