Job description

body> Contract Senior AI Engineer - Agentic AI & Platform Assessment (Costa Rica / Ecuador) Posted on 20 August 26 by Laks • • $ - $ Powered by Tracker Back to Jobs Job Description Role: Senior AI Engineer - Agentic AI & Platform Assessment Location: LATAM / Nearshore, Remote Country of preference : Costa Rica, Ecuador is Option 2 but we prefer Costa Rica. Experience: 8+ Years Role Overview We are seeking a hands-on Senior AI Engineer to support the technical hardening assessment of an AI-enabled, multi-tenant digital marketplace platform. The role will focus on reviewing the platforms existing AI and agentic engineering surfaces, identifying security, reliability, governance and quality risks, and providing evidence-based recommendations for future remediation. Key Responsibilities AI & Agentic Architecture Assessment - Review existing LLM, AI-agent and MCP-based capabilities across the platform. - Trace AI workflows from prompt/input through model invocation, tool use, response handling and downstream data writes. - Assess model selection, routing, configuration and model-version management. - Evaluate existing AI-assisted engineering patterns and guardrails. AI Security & Governance - Identify prompt-injection and indirect prompt-injection attack surfaces. - Assess validation of LLM outputs before database or application writes. - Review tool permissions, authorization boundaries, tenant isolation and agent access controls. - Evaluate auditability of AI actions including prompts, responses, tool calls and resulting transactions. - Review token usage, model cost controls and opportunities for cost governance. Quality, Reliability & Productivity - Assess handling of hallucination, malformed responses, model failures and prompt/model drift. - Review structured-output/schema-validation patterns and AI-generated test quality. - Assess how AI coding agents are used within the SDLC and whether engineering guardrails are consistently enforced. - Recommend measurable productivity, quality and reliability metrics for agentic engineering. Assessment Deliverables - Produce evidence-backed findings with severity, impact and recommended remediation. - Contribute to the AI-specific portion of the hardening scorecard and 30/60/90 roadmap. - Work closely with the Solution Architect and Senior Full-Stack Engineer during findings validation and prioritization. Required Technical Skills & Competencies 7+ years of software engineering experience with strong hands-on Generative AI / LLM engineering experience. Production experience integrating LLMs such as Claude, OpenAI models or equivalent. Strong experience with LLM APIs, structured outputs, function/tool calling and agentic workflows. Practical experience with Model Context Protocol (MCP) or comparable agent/tool integration patterns. Strong understanding of prompt injection, LLM security and AI application attack surfaces. Experience with schema validation, API integration and application/database write paths. Strong knowledge of software engineering, REST APIs and modern cloud-native applications. Experience reviewing existing production code and identifying technical, security and governance risks. Understanding of multi-tenant SaaS security and authorization patterns. Good to Have Experience with Claude / Anthropic SDK and Claude Code. Experience with Supabase, PostgreSQL and Edge Functions. Experience with RAG, intelligent matching or recommendation systems. Experience building AI-enabled marketplace or workflow platforms. Familiarity with AI governance for government, public-sector or regulated environments. Exposure to MCP servers and AI-enabled API ecosystems. Experience measuring AI-assisted engineering productivity. Must-Have Skills Hands-on Generative AI / LLM engineering. Agentic AI and tool-calling architecture. Prompt-injection and AI security knowledge. LLM output validation and governance. Strong code-review and troubleshooting skills. Ability to collaborate with architects and application engineers. Ability to work during U.S. business hours. Desired Attributes Strong analytical and investigative mindset. Evidence-driven and comfortable challenging existing AI implementation patterns. Strong ownership mindset and engineering discipline. Clear communicator with senior technical stakeholders. Comfortable working in a short, outcome-driven assessment engagement. Apply Now Job Information Rate / Salary $ - $ Sector Not Specified Category Not Specified Skills / Experience Not Specified Benefits Not Specified Our Reference JOB-7492 Job Location

Requirements

Must-haves

Senior AI Engineer - Agentic AI & Platform Assessment (Costa Rica / Ecuador)
Posted on 20 August 26 by Laks
Powered by Tracker
Back to Jobs
Role: Senior AI Engineer - Agentic AI & Platform Assessment
Location: LATAM / Nearshore, Remote
Country of preference : Costa Rica, Ecuador is Option 2 but we prefer Costa Rica.
Experience: 8+ Years
We are seeking a hands-on Senior AI Engineer to support the technical hardening assessment of an AI-enabled, multi-tenant digital marketplace platform.
AI & Agentic Architecture Assessment
Review existing LLM, AI-agent and MCP-based capabilities across the platform.
Trace AI workflows from prompt/input through model invocation, tool use, response handling and downstream data writes.
Assess model selection, routing, configuration and model-version management.
Evaluate existing AI-assisted engineering patterns and guardrails.
AI Security & Governance
Identify prompt-injection and indirect prompt-injection attack surfaces.
Assess validation of LLM outputs before database or application writes.
Review tool permissions, authorization boundaries, tenant isolation and agent access controls.
Evaluate auditability of AI actions including prompts, responses, tool calls and resulting transactions.
Review token usage, model cost controls and opportunities for cost governance.
Quality, Reliability & Productivity
Assess handling of hallucination, malformed responses, model failures and prompt/model drift.
Review structured-output/schema-validation patterns and AI-generated test quality.
Assess how AI coding agents are used within the SDLC and whether engineering guardrails are consistently enforced.

Nice-to-haves

None flagged.

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aillmapirest

Platform: careers-html
Effort: medium