AI / Agent Developer

About Bolt

Bolt is shaping a future where cities are built for people, not cars. What started as an ambitious project of a 19-year-old in 2013 has grown into a global mobility platform used by more than 200 million customers and 4.5 million driver and courier partners across 50 countries.

From ride-hailing and food delivery to scooters, e-bikes, and car-sharing, Bolt helps people move through cities every day. Small, autonomous teams drive this work, combining the speed and ownership of a startup with the scale of a global technology company backed by more than 1bn in funding.

And we're just getting started.

About the role

As an AI / Agent Developer youll build and operate AI agents and LLM-powered automation that remove manual effort from Bolts internal people processes. Working closely with the Senior AI/Agent Engineer, you'll take well-defined agents, workflows, and components from implementation through evaluation, testing, release, and production support. You'll build within established architecture, platform standards, and boundaries for autonomous action, while contributing your judgement and raising questions when requirements or designs need clarification. This is an opportunity to grow your agentic engineering experience by building real production systems, where correctness and auditability are critical due to the sensitive employee data and processes involved.

Main tasks and responsibilities:

• Building and delivering production AI agents, automated workflows, and multi-step LLM pipelines, including safe tool interactions, human-in-the-loop checkpoints, automated tests, evaluations, and releases.
• Ensuring the quality and reliability of agentic systems by maintaining evaluation and regression suites, investigating failures, and implementing logging, monitoring, alerting, audit trails, and cost controls.
• Supporting agents and automations in production by troubleshooting and fixing bugs, regressions, and failure modes, while safely managing retries and protecting data integrity.
• Applying strong security, privacy, and data protection practices, including scoped permissions and data minimisation when handling sensitive employee data.
• Maintaining clear technical documentation and JIRA tasks, and contributing constructively to code and design reviews while incorporating feedback from senior engineers.
• Collaborating with engineering and People teams to understand the processes you automate, identify improvement opportunities, resolve data quality issues, and share knowledge and relevant developments in agentic AI.

About you:

• You have strong Python skills and can work confidently and carefully within an existing production codebase.
• You have practical experience building LLM-powered features or AI agents through professional, academic, or personal projects and understand how production systems differ from prototypes.
• You understand API integrations, asynchronous processing, and the challenges of building reliable workflows across distributed systems.
• You're familiar with evaluating non-deterministic AI systems and are willing to build the testing and evaluation infrastructure needed to make agents reliable and trustworthy.
• You have sound judgement about when to ask rather than assume, communicate technical concepts clearly to non-technical colleagues, and raise questions when requirements or system behaviour are unclear.
• You handle sensitive personal data with care and understand the importance of correctness, privacy, and appropriate safeguards when building systems that act on employee data.

• You have strong Python skills and can work confidently and carefully within an existing production codebase.
• You have practical experience building LLM-powered features or AI agents through professional, academic, or personal projects and understand how production systems differ from prototypes.
• You understand API integrations, asynchronous processing, and the challenges of building reliable workflows across distributed systems.
• You're familiar with evaluating non-deterministic AI systems and are willing to build the testing and evaluation infrastructure needed to make agents reliable and trustworthy.
• You have sound judgement about when to ask rather than assume, communicate technical concepts clearly to non-technical colleagues, and raise questions when requirements or system behaviour are unclear.
• You handle sensitive personal data with care and understand the importance of correctness, privacy, and appropriate safeguards when building systems that act on employee data.

• Accelerate your professional growth with unique career opportunities.
• Enjoy a rewarding salary and stock options, knowing that as Bolt succeeds, so do you.
• Take care of your physical and mental health with our wellness perks.
• Celebrate 5 years at Bolt with a 1-month paid sabbatical to recharge.
• Connect with colleagues at annual company events and smaller team gatherings.
• Balance flexibility and in-person collaboration with our hybrid model, including at least 12 monthly in-office days.