Skip to content
BenchlingBenchlingUnited States

Agentic AI Engineer

Founding engineer owning architecture and delivery of enterprise agentic AI systems. Hands-on builder of LLM orchestration, tool integrations, memory, evaluation, and production-grade infrastructure.

176k – 265k
Remote7+ YOEML Engineering

About the role

Responsibilities

  • Define foundational architecture for enterprise agentic AI: orchestration, agent frameworks, tool integrations (MCP), memory/state management, evaluation, observability
  • Make documented build vs. buy decisions across the stack
  • Write production code at least half the time; stand up CI/CD, testing, evaluation, and deployment infrastructure for agentic systems
  • Graduate prototypes into hardened, production-grade systems under a "you build it, you run it" model
  • Design for multi-tenant isolation, secrets management, audit logging, payload encryption, RBAC, and human-in-the-loop controls
  • Partner with Security Engineering on threat modeling for prompt injection, tool misuse, data exfiltration
  • Coach power users and departmental teams on production patterns; develop criteria for graduating prototypes to enterprise systems
  • Build internal developer experience: templates, SDKs, sandboxes for safe external builder use
  • Partner with Data, Analytics & Systems on source-of-truth datasets and pipelines
  • Set bar for code quality, testing/evaluation, documentation, on-call practices
  • Drive technical hiring and mentor engineers

Requirements

  • 7+ years professional software engineering experience building production systems with strong systems design
  • Hands-on experience building production LLM/agentic systems: orchestration, tool use, memory/state management, evaluation, observability
  • Production experience with at least two of: Python, TypeScript/Node.js, Go
  • Hands-on expertise with LLM APIs (OpenAI, Anthropic), agentic frameworks (LangChain, CrewAI), RAG over business content, vector databases (pgvector, Pinecone), workflow automation (n8n, Langflow), LLM observability (LangSmith, Arize)
  • Track record building a platform/function/product area from zero to one and scaling it
  • Experience in regulated or security-sensitive environments; grasp of encryption, access controls, audit logging, secrets management
  • Comfort exercising technical leadership independent of positional authority
  • Product-first mindset; strong communication with technical and non-technical audiences

Nice to Have

  • Background in enterprise SaaS, life sciences, or biotech
  • Familiarity with LangGraph, MCP, agent SDKs from model providers
  • Experience with async orchestration (Temporal, Prefect, Airflow) for long-running/agentic workflows
  • Familiarity with SOC 2, HIPAA, or GxP compliance

Skills

PythonTypeScriptGoLangChainCrewaiOpenAI APIClaude APIPgvectorPineconeLangsmithRAGVector DatabasesLlm ObservabilityAgentic FrameworksMcp

Similar roles

ML Engineering jobs
Benchling

Agentic AI Engineer

BenchlingSan Francisco, CA

Founding engineer building enterprise-grade agentic AI systems at Benchling, owning architecture, production code, and cross-functional enablement for LLM orchestration and internal tooling.

176k – 265k
Hybrid7+ YOEML Engineering
Zilliz

Senior Software Engineer, Vector Index Research

ZillizRedwood City, CA

Research and implement high-performance vector indexing and retrieval algorithms for Milvus and Zilliz Cloud. Requires 3+ years in vector search or HPC, strong C++ or Rust skills, and a research-driven engineering mindset.

175k – 250k
Hybrid3+ YOEML Engineering
Mem0

Senior Research Engineer

Mem0San Francisco, CA

Own the end-to-end lifecycle of memory features for AI agents. Fine-tune models, implement research, build evaluations, and ship production systems with Engineering.

175k – 250k
On-site7+ YOEML Engineering
AKASA

Sr. Machine Learning Engineer

AKASASouth San Francisco, CA

As a Senior Machine Learning Engineer, you will develop and deploy state-of-the-art ML solutions for healthcare problems, working with large medical datasets and owning ML services end-to-end. This role requires expertise in LLMs, cloud platforms, and ML frameworks.

175k – 230k
Hybrid5+ YOEML Engineering
Applied Intuition

Applied Perception Engineering Lead

Applied IntuitionAnn Arbor, MI

Lead a team of software engineers to develop and integrate perception pipelines for various modalities and an autonomy service for government and defense applications. This role focuses on deploying software to hardware and integrating pre-trained ML models.

175k – 210k
On-site8+ YOEML Engineering