CommandLink - AI Engineer, LLM Systems & Agentic Workflows

AI Engineer, LLM Systems & Agentic Workflows

CommandLinkvia Glassdoor
RemotoRemotoPlenoCLT3 dias atrás

Salário Estimado

R$ 9.867,00 - R$ 14.801,00

0de 100

Excelente

Score da Vaga

Descrição da Vaga

Command|Link Command|Link is a global SaaS Platform providing network, voice services, and IT security solutions, helping corporations consolidate their core infrastructure into a single vendor and layering on a proprietary single pane of glass platform.


Command|Link has revolutionized the IT industry by tackling the problems our competitors create.


In recognition for our unprecedented innovation and dedication, Command|Link was recognized as the SD-WAN Product of the Year, ITSM Visionary Spotlight, UCaaS Product of the Year, NaaS Product of the Year, Supplier of the Year, and the AT&T Strategic Growth Partner.


Command|Link has built the only IT platform for scale that solves ISP vendor sprawl and IT headaches.


We make it easy for our customers to get more done, maximize uptime and improve the bottom line.


Learn more about us here! This is a 100% remote position About your new role: As an AI Engineer focused on LLM Systems, your primary mandate is to design, build, and operate the AI layer that powers intelligent automation across the CommandLink platform.


You'll be working at the engineering layer of agentic AI: building durable, production-grade LLM workflows on top of Temporal, implementing security and policy controls around LLM execution, and solving hard problems around prompt injection, output trust, and runtime governance in domain-specific contexts.


You'll work closely with Engineering and Product leads to build agentic workflows to execute deterministic workflows for context aware insights, triage, investigations and remediation into reliable, observable, and policy-compliant AI workflows.


That means designing for failure, latency, and adversarial inputs from day one, not retrofitting safety controls after the fact.


The space is moving fast, the problems are genuinely unsolved, and we're looking for someone who has strong opinions about how to build AI systems that are trustworthy in production.


Key Responsibilities:

Agentic workflow engineering: design and build multi-step LLM workflows using Temporal as the durable orchestration backbone; handling retries, state, parallelism, human-in-the-loop steps, and long-running agent execution
Domain-specific automation: work with subject matter experts to identify, scope, and implement AI-driven automation for specific business and operational domains; own the full delivery from prototype to production • LLM security and policy enforcement: implement runtime policy controls around LLM execution, including prompt injection mitigation, output validation, privilege separation (dual-LLM / quarantined execution patterns), and integration with policy engines
Parallel and live evaluation: build evaluation frameworks to assess LLM output quality in parallel with production traffic; implement continuous evals, regression detection, and automated quality gates • Prompt injection defense: apply and adapt state-of-the-art design patterns including the Dual LLM, Plan-Then-Execute, and Code-Then-Execute patterns to harden agent pipelines against adversarial inputs
Policy engine integration: integrate tools such as Sequrity.ai to define, enforce, and audit natural-language security policies over LLM tool use and execution paths • Observability and auditability: instrument AI workflows with full event history, structured logging of prompts and completions, cost tracking, and latency profiling making the behavior of AI systems traceable and debuggable
LLM steering and control: implement output steering strategies, structured generation, constrained decoding, and fallback routing to ensure models behave within defined operational envelopes • Collaborate on architecture: work across the engineering team to define standards for how AI capabilities are integrated into the product setting patterns others will follow What You'll Need for Success Essential:
Experience with complex and large datasets • 2+ years building production LLM-powered applications beyond RAG prototypes; real systems handling real failure modes
Hands-on experience with Temporal (or equivalent durable execution platforms such as Cadence or Conductor) for orchestrating multi-step, long-running AI workflows • Deep understanding of prompt injection attack vectors, mitigation strategies, and the trade-offs between defense patterns (Dual LLM, CaMeL / Code-Then-Execute, Action-Selector, context minimization)
Experience implementing policy controls and guardrails around LLM execution RBAC/PBAC for agents, output filtering, semantic validation, and tool-use restrictions • Practical experience building parallel evaluation pipelines for LLM outputs live evals, shadow scoring, regression suites, and automated quality gates
Strong software engineering fundamentals.

You write maintainable, testable code; experience in Python and/or Go preferred • Familiarity with LLM APIs and inference providers (OpenAI, Anthropic, Mistral, or open-weight models via vLLM / Ollama)

Understanding of agentic architecture patterns: tool use, multi-agent delegation, structured outputs, memory and context management • Experience integrating LLM systems with external tools and APIs in a secure, auditable way
Experience with langchain or other agentic frameworks Nice to Have:
Experience with dedicated policy engines for LLM security such as Sequrity.ai, LLM Guard, or equivalent TOML/rules-based policy frameworks
Familiarity with OWASP LLM Top 10 and NIST AI RMF compliance requirements • Experience with structured generation frameworks (Outlines, Instructor, Guidance) for constrained LLM outputs
Knowledge of chaos and adversarial testing for AI systems; red-teaming, jailbreak evaluation, and automated adversarial prompt suites • Experience with open-weight model deployment (vLLM, TGI, Ollama) and inference optimization
Familiarity with MCP (Model Context Protocol) and other protocols for standardised agent tool integration • Background in security engineering, particularly application-layer threat modelling and or networking and device management
Takes on additional responsibilities and projects as needed to support the success of the team and organization.

Why you'll love life at Command|Link Join us at CommandLink, where you'll have the opportunity to shape the future of business communication.


We value the innovative spirit and seek individuals ready to bring their unique vision and expertise to a team that values bold ideas and strategic thinking.


Are you ready to make an impact? Apply now and be the architect of your career as well as our clients' success. • Room to grow at a high-growth company

An environment that celebrates ideas and innovation • Your work will have a tangible impact
Flexible time off • Fun events at cool locations
Employee referral bonuses to encourage the addition of great new people to the team At CommandLink, we’re committed to creating a fair, consistent, and efficient hiring experience.

As part of our process, we use AI-assisted tools to help review and analyze applications.


These tools support our recruiting team by identifying qualifications and experience that align with the requirements of each role.


AI tools are used only to assist in the evaluation process — they do not make final hiring decisions.


Every application is reviewed by a member of our recruiting or hiring team before any decisions are made.

Vagas Semelhantes

RemotoRemoto6 dias atrás

R$ 10k - 15k/mês

PlenoCLT

Role Overview We are hiring a Python Developer to build backend APIs, data pipelines, and AI-powered features. In this role, you will write production Python every day using modern frameworks such as FastAPI, Django, or Flask. The ideal candidate has strong Python fundamentals, writes well-tested co...

Accenture Federal Services - Vaga Generative AI Applications Engineer (Agents & RAG)

Generative AI Applications Engineer (Agents & RAG)

Accenture Federal ServicesGlassdoor
RemotoRemoto29 dias atrás

R$ 9k - 17k/mês

PlenoCLT

At Accenture Federal Services, nothing matters more than helping the US federal government make the nation stronger and safer and life better for people. Our 13,000+ people are united in a shared purpose to pursue the limitless potential of technology and ingenuity for clients across defense, nation...

RemotoRemoto28 dias atrás

R$ 10k - 13k/mês

SêniorCLT

Senior Full Stack Software Engineer (Remote) Location: Remote (US-based) Reports to: CTO, SportsRecruits About SportsRecruits SportsRecruits is the leading sports recruiting network, connecting athletes, clubs, events, and college coaches in the recruiting process. The company’s network and tools ar...

International Business Consultants LLC. - Vaga Full-Stack Developer React & Python

Full-Stack Developer React & Python

International Business Consultants LLC.LinkedIn
RemotoRemoto4 dias atrás

R$ 5k - 8k/mês

JúniorCLT

Must be Green Card or Citizen Company Description International Business Consultants (IBC) is a global strategic consulting firm specializing in digital transformation, enterprise agility, and AI-powered solutions. We collaborate with Fortune 500 companies, government agencies, and innovative organi...

Interessado nesta vaga?

Candidatar-se

Você será redirecionado para o site original

Informações

NívelPleno
ContratoCLT
LocalRemoto
RemotoSim
MoedaBRL
Publicada3 dias atrás
FonteGlassdoor

Análise de Vaga com IA

Estimativa salarial, match de tecnologias e análise de requisitos feitos com Inteligência Artificial

Quer se preparar melhor? Pratique entrevistas com IA no Recrutadoria ou melhore suas habilidades no BitMentor

← Voltar às Vagas