Senior AI Engineer, Agentic Systems in United States at Jobgether

This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Senior AI Engineer, Agentic Systems based in United States.

This is a high-impact engineering role focused on designing and delivering production-grade agentic AI systems that orchestrate tools, data, and policies to solve real enterprise workflows.
You will work at the forefront of applied generative AI, building modular, scalable systems that power real business outcomes in complex environments.
The role blends architecture, hands-on engineering, and client-facing problem solving, with a strong emphasis on reliability, security, and measurable performance.
You will design multi-agent systems, implement RAG pipelines, and integrate enterprise tools into cohesive AI-driven workflows.
The environment is fast-moving, experimental, and deeply technical, with a strong focus on shipping production-ready systems rather than prototypes.
You will collaborate directly with enterprise clients and internal teams to translate real-world processes into robust AI solutions.
This role is ideal for an engineer who thrives in greenfield architecture and enjoys turning cutting-edge AI capabilities into practical, scalable systems.

• Design and implement multi-agent architectures with robust state management, memory systems, routing logic, and modular components such as planners, tool registries, and policy guards
• Evaluate and apply agentic frameworks such as LangGraph, LangChain Agents, AutoGen, CrewAI, LlamaIndex Agents, Semantic Kernel, or Haystack, including trade-off analysis
• Build and optimize retrieval-augmented generation (RAG) pipelines using vector databases and structured knowledge sources, ensuring grounding and relevance
• Integrate enterprise systems and data sources through APIs, function calling, event-driven architectures, and workflow orchestration tools
• Define and enforce reliability standards including SLIs/SLOs, observability, tracing, logging, and performance monitoring for agentic workflows
• Develop evaluation frameworks using automated and human-in-the-loop methods to measure accuracy, safety, cost, and task success
• Implement CI/CD pipelines, canary deployments, feature flags, and environment promotion strategies for production AI systems
• Enforce safety, privacy, and governance policies including data minimization, access control, redaction, and auditability
• Collaborate directly with enterprise clients to translate business processes into production-grade AI systems and validate solutions through proofs of value

Requirements:

• 5–8+ years of experience in software engineering or platform engineering, with recent hands-on experience building production LLM or AI systems
• Strong experience with agentic frameworks such as LangGraph, LangChain Agents, AutoGen, CrewAI, or equivalent systems
• Deep understanding of RAG architectures including embedding strategies, vector databases, chunking, ranking, and grounding techniques
• Proven ability to build observable, secure, and cost-efficient AI systems with strong engineering discipline around testing and CI/CD
• Strong software engineering fundamentals in Python or TypeScript, including async programming, APIs, and distributed system design
• Experience implementing evaluation, monitoring, and observability systems for AI workflows (e.g., tracing, metrics, prompt evaluation tools)
• Familiarity with enterprise security, privacy, and compliance requirements (e.g., IAM, PII handling, data governance)
• Strong communication skills with the ability to work directly with clients and translate requirements into technical designs
• Experience with Azure or other cloud platforms (AWS/GCP) and containerized deployment environments is highly valued
• Familiarity with structured outputs, constrained decoding, and schema-based AI workflows is a plus

Benefits:

• Competitive and flexible compensation package aligned with experience and impact, potentially including base salary, performance incentives, and equity participation
• Remote-first flexibility with US-based working arrangements and cross-time-zone collaboration opportunities
• Opportunity to work on cutting-edge production agentic AI systems for enterprise clients
• High autonomy in system design, architecture decisions, and technical execution
• Strong culture of learning, experimentation, and knowledge sharing, including technical deep dives and internal workshops
• Exposure to modern AI tooling, frameworks, and enterprise-scale deployments
• Inclusive and flexible work environment focused on meaningful, high-impact engineering work
• Opportunity to shape foundational AI systems used in real business-critical workflows