Strativ Group
Senior Machine Learning Engineer - Agentic Systems (Fremont)
Strativ Group, Fremont, California, United States, 94537
Senior Machine Learning Engineer - Agentic Systems
We are partnered with a highly technical AI research company building advanced AI systems capable of operating across complex, real-world engineering environments. The company is well-funded, executing large-scale programs, and pushing the frontier of AI systems that can reason, plan, and act reliably in the physical world.
Their platform focuses on enabling intelligent agents to operate end-to-end engineering workflows - combining large language models with structured planning, deterministic execution, and real system constraints. This work sits at the intersection of AI research, systems engineering, and applied infrastructure, with a strong emphasis on safety, reproducibility, and first-principles design. The team consists of deeply technical engineers and researchers with backgrounds spanning ML systems, distributed infrastructure, and applied AI. They operate in a high-ownership environment where individuals design and ship foundational systems that enable entirely new classes of agentic behavior.
They are hiring a Senior ML Engineer to design and build the core planning and orchestration layers that allow LLM-based agents to reliably execute multi-step engineering tasks. You will work closely with systems, data, and ML teams to integrate agent workflows into real production toolchains. This role offers deep technical ownership and the opportunity to shape how intelligent agents interact with complex systems at scale.
What Youll Work On
Designing and implementing agent planners, orchestration flows, and state machines using modern agent frameworks Building deterministic tool-calling pipelines with structured schemas and traceable execution paths Developing action adapters and cross-tool interfaces that enable safe, reproducible agent behavior Implementing robust error handling, retries, timeouts, rollbacks, and replay mechanisms Collaborating across systems architecture, data infrastructure, and ML teams to deploy agents into real engineering environments
Key Experience Required
Strong experience building agent systems, LLM orchestration frameworks, or structured tool-calling pipelines Deep intuition for schemas, action abstractions, deterministic execution, and reproducibility Experience reasoning about system-level failure modes, edge cases, and safe tool interaction Comfort operating across AI models, systems engineering, and domain-specific tooling A builders mindset - you enjoy ambiguous problems, first-principles design, and owning systems end-to-end
Above all, they are looking for engineers who demonstrate exceptional technical depth, strong ownership, and the ability to build reliable agent systems that operate under real-world constraints.
Please apply ASAP if interested.
We are partnered with a highly technical AI research company building advanced AI systems capable of operating across complex, real-world engineering environments. The company is well-funded, executing large-scale programs, and pushing the frontier of AI systems that can reason, plan, and act reliably in the physical world.
Their platform focuses on enabling intelligent agents to operate end-to-end engineering workflows - combining large language models with structured planning, deterministic execution, and real system constraints. This work sits at the intersection of AI research, systems engineering, and applied infrastructure, with a strong emphasis on safety, reproducibility, and first-principles design. The team consists of deeply technical engineers and researchers with backgrounds spanning ML systems, distributed infrastructure, and applied AI. They operate in a high-ownership environment where individuals design and ship foundational systems that enable entirely new classes of agentic behavior.
They are hiring a Senior ML Engineer to design and build the core planning and orchestration layers that allow LLM-based agents to reliably execute multi-step engineering tasks. You will work closely with systems, data, and ML teams to integrate agent workflows into real production toolchains. This role offers deep technical ownership and the opportunity to shape how intelligent agents interact with complex systems at scale.
What Youll Work On
Designing and implementing agent planners, orchestration flows, and state machines using modern agent frameworks Building deterministic tool-calling pipelines with structured schemas and traceable execution paths Developing action adapters and cross-tool interfaces that enable safe, reproducible agent behavior Implementing robust error handling, retries, timeouts, rollbacks, and replay mechanisms Collaborating across systems architecture, data infrastructure, and ML teams to deploy agents into real engineering environments
Key Experience Required
Strong experience building agent systems, LLM orchestration frameworks, or structured tool-calling pipelines Deep intuition for schemas, action abstractions, deterministic execution, and reproducibility Experience reasoning about system-level failure modes, edge cases, and safe tool interaction Comfort operating across AI models, systems engineering, and domain-specific tooling A builders mindset - you enjoy ambiguous problems, first-principles design, and owning systems end-to-end
Above all, they are looking for engineers who demonstrate exceptional technical depth, strong ownership, and the ability to build reliable agent systems that operate under real-world constraints.
Please apply ASAP if interested.