Senior AI Engineer

Sourced from apply.workable.com

Design and build the software layer that lets language models carry multi-step tasks to completion, covering tooling, context, state, and feedback. Work spans rapid prototyping, evaluation, and hardening for reliable production use, with ownership at every stage. The role suits an engineer who wants to shape how much independent action automated systems should take.

• Build scaffolding that gives language models tools, context, and execution environments to finish multi-step tasks
• Define how agents plan, act, track state, recover from errors, and hand work back to people
• Prototype AI-driven features, test them on real user problems, and move the strongest into production
• Create evaluation suites that score task completion and decision quality, turning production failures into repeatable test cases
• Diagnose faults across the stack, from model instructions through tool connections and workflow sequencing
• Set explicit access limits and review points for agent autonomy
• Test new models and techniques for capability, reliability, latency, and cost
• Build reusable tooling to ship features faster and operate them more easily

• Strong software engineering skills and a track record building agent systems that take actions and finish tasks
• Working knowledge of harness design, context handling, and tool interfaces
• Experience writing evals, reading execution traces, and fixing unreliable behavior
• Ability to prototype quickly and judge what needs hardening before release
• Sound judgment about agent autonomy and when to involve a person
• Background building, launching, running, and fixing production software
• Early-stage start-up experience
• Around 1 to 1.5 years of applied experience developing language model or agent software such as orchestration layers, function calling, and evaluation pipelines

• Computer science degree from a top 50 US university
• Familiarity with long-running agents including reliable execution, progress tracking, retry logic, and fault recovery
• Exposure to agents that write code, operate browsers or desktops, or coordinate multiple tools
• Experience creating test frameworks, simulated environments, or utilities for reviewing agent sessions
• Delivering AI-enabled product features in a compact team