10 hours ago
Remote, PeruSenior
Responsibilities
- Translate client business problems into scalable, production-ready agentic AI solutions.
- Design and implement multi-step agent systems with orchestration, tool and function calling, task decomposition, and multi-agent coordination where appropriate.
- Integrate agents with enterprise systems using APIs, MCP servers, and structured tool contracts.
- Build evaluation frameworks, guardrails, grounding and citation checks, and human-in-the-loop workflows.
- Instrument systems for traceability and observability across agent actions, model behavior, token and cost usage, latency, and performance.
- Design state and memory management, model routing, retries, idempotency, and other production reliability patterns.
- Build and deploy AI solutions using Azure or AWS cloud platforms and related AI and infrastructure services.
- Apply software engineering practices using Python or Java, automated testing, source control, and CI/CD.
- Collaborate with client engineering and security teams on architecture reviews, threat modeling, security reviews, audits, and enterprise delivery requirements.
- Convert successful client approaches into reusable patterns and solutions for Zeal.
Requirements
- Hands-on experience designing and shipping production agentic AI systems involving tool or function calling, multi-step workflows, orchestration, task decomposition, or multi-agent architectures.
- Experience evaluating agent behavior and building evaluation harnesses, guardrails, grounding checks, human-in-the-loop controls, and failure mitigation mechanisms.
- Deep hands-on experience with either Azure or AWS and surrounding AI and infrastructure services.
- Strong proficiency in Python or Java, API design, containers, automated testing, source control, and CI/CD.
- Enough machine learning knowledge to determine when traditional machine learning or deterministic approaches are more appropriate than an LLM.
- Experience delivering software in large organizations with role-based access, data isolation, security reviews, compliance, change control, and production governance requirements.
- Experience with agent traceability, state and memory management, model routing, latency and cost visibility, retries, and idempotency.
- Excellent verbal and written communication skills with the ability to explain AI systems, decisions, risks, and tradeoffs to technical and non-technical stakeholders.
- Strong technical judgment and problem-solving ability, including recognizing when agentic solutions introduce unnecessary complexity.
- Experience with MCP, emerging tool-interoperability standards, evaluation frameworks such as RAGAS, fine-tuning, model distillation or optimization, or regulated industries is helpful but not required.
Benefits
- Work with passionate, talented colleagues in a kind, generous, and collaborative environment.
- Consult for Fortune 1000 companies across industries and technical stacks, with varied projects and significant impact.
- Role available across the company’s primary LATAM hub in Peru.
- Hiring process may include a preliminary phone interview, video interviews, and a take-home exercise with up to one week for completion.
Categories
About Livefront
Livefront is a digital product consultancy that designs and builds mobile, web, and AI-enabled experiences for enterprises and startups. The privately held firm, founded in 2001 and headquartered in Minneapolis, provides strategy, design, and software engineering services on a client-services model. Notable clients have included CVS, Samsung, General Mills, Optum, and startups such as HomeSpotter and Credly.