Senior AI SRE Engineer

<p></p> <p><strong>Job Title:</strong> Senior AI SRE Engineer</p> <p><strong>Key Skills:</strong> Agentic AI, Python, Go, LLMs, MCP, LangChain, PyTorch, TensorFlow, DevOps, Docker, Kubernetes, RAG, AI Security, Observability</p> <p><strong>Experience:</strong> 3–5 YOE</p> <p><strong>Location:</strong> San José, Costa Rica</p> <p><strong>Mode:</strong> Hybrid – 2–3 days per week on-site</p> <p>We at Coforge are hiring <strong>Senior AI SRE Engineer (#006fu00000QeELXAA3-10)</strong> with the following skill set.</p> <p><strong>Key Responsibilities</strong></p> <ul> <li> <p>Design and deploy intelligent agent systems for enterprise workflows, including MCP integrations with DevOps tools such as GitHub, Jenkins, and Jira.</p> </li> <li> <p>Build Python and Go services and APIs to integrate AI capabilities with enterprise platforms and systems.</p> </li> <li> <p>Implement context augmentation, AI security guardrails, and evaluation pipelines to ensure reliable, safe, and high-performing AI solutions.</p> </li> <li> <p>Develop observability solutions to monitor agent actions, usage, and anomalies while collaborating with cross-functional teams and documenting best practices.</p> </li> </ul> <p><strong>Required Skills &amp; Qualifications</strong></p> <ul> <li> <p>Bachelor’s or master’s degree in Computer Science, Engineering, or a related field, or equivalent experience.</p> </li> <li> <p>3–5 years of relevant experience.</p> </li> <li> <p>Strong programming skills in Python and Go, with experience building production-grade distributed systems.</p> </li> <li> <p>Hands-on experience with LLMs, NLP, and AI frameworks such as PyTorch, TensorFlow, LangChain, or Ray.</p> </li> <li> <p>Experience with DevOps tools such as GitHub, GitLab, Jenkins, Jira, ArgoCD, and Artifactory, including API integrations.</p> </li> <li> <p>Familiarity with secure software development, authentication, and access control mechanisms.</p> </li> <li> <p>Knowledge of cloud-native platforms and containerized environments, including Docker and Kubernetes.</p> </li> <li> <p>Strong debugging and problem-solving skills.</p> </li> </ul> <p><strong>Preferred Skills:</strong></p> <ul> <li> <p>Experience building MCP services or similar AI integration frameworks.</p> </li> <li> <p>Knowledge of AI security practices, including guardrails, adversarial testing, red teaming, and policy enforcement.</p> </li>