This list contains only the countries for which job offers have been published in the selected language (e.g., in the French version, only job offers written in French are displayed, and in the English version, only those in English).
Cognitive Space builds next-generation AI systems that help “supercharge satellite operations” through its CNTIENT platform. We are seeking an engineer who thrives in a dynamic, fast-paced environment and enjoys taking ideas from theory into production deployments. You will play a critical role in designing and shipping production-grade, tool-using, multi-agent LLM systems that can coordinate specialized components (e.g., planning, retrieval, decisioning, and execution) to complete complex, multi-step workflows in operational environments. This role is for a hands-on builder who can translate ambiguous workflow requirements into reliable multi-agent behavior, robust tool integrations, and measurable outcomes. Experience deploying and optimizing LLM solutions, including open-source model deployments and work in controlled or mission environments, is strongly valued.
Job Responsibility:
Design and build LLM-based agents that can plan and execute multi-step workflows (task decomposition, state management, memory, and controlled autonomy)
Implement and maintain a robust tool interface layer (tool schemas/contracts, structured I/O, validation, retries, idempotency, and safe execution boundaries)
Integrate agents with internal and external systems: APIs, databases, queues, and operational services, ensuring reliable action-taking and traceability
Develop evaluation and regression testing for agent behavior (scenario suites, golden traces, automated quality gates) to reduce drift and ensure predictable performance
Establish observability for agent runs (tracing, failure analysis, latency/cost monitoring, tool-call success rates) and drive continuous improvements
Containerize and deploy agent services and decision-making capabilities for production and edge environments, as applicable
Collaborate with cross-functional teams to identify and prioritize agentic automation opportunities tied to key milestones and requirements
Implement safety and governance controls (permissions, policy checks, audit logs, and appropriate handling of sensitive data) aligned to operational constraints
Requirements:
US Citizenship
Active TS/SCI clearance preferred or must be able to obtain and maintain a TS/SCI Clearance
Preferred Security+ Certification
Bachelor’s/Master's/Ph.D. in a relevant field: Computer Science, Engineering, Applied Math, Statistics, etc.
2–5+ years of professional experience as an AI Engineer, ML Engineer, Software Engineer (Applied AI), Applied Scientist, or similar role
Strong programming skills in Python
experience with production services, APIs, and containerization (Docker/Kubernetes) is strongly preferred
Experience deploying and operating workloads on AWS (e.g., IAM, VPC, EC2, EKS/ECS, Lambda, S3, CloudWatch), including security, monitoring, and cost-aware design
Hands-on experience building LLM applications in production
Experience with ML/LLM frameworks and ecosystems (e.g., PyTorch/TensorFlow familiarity
LangChain/Strands/Bedrock familiarity
vector databases/search) consistent with an applied engineering role
Strong debugging and analytical skills: ability to diagnose failures across model behavior, tool execution, and system integration
Ability to convey complex technical behavior and trade-offs in a clear, practical manner
Nice to have:
Prefer experience in space/satellite/aerospace domains, mission operations, systems engineering, or adjacent operational environments
Prefer experience with offline/online evaluation methodologies and building reusable test harnesses for AI behavior
What we offer:
Equity in the form of options
Flexible Time-Off policy and company holidays
Cost-effective health care, dental, and vision with company contributions