Clera
Software Engineer
- Compensation
- $130K–$220K / yr
- From job posting
- Location
- San Francisco, CA, US
- Arrangement
- On-site
- Employment type
- Full-time
- Posted
- 27 September 2026 (3 days ago)
Checked 2 days agoApplications go to the employer, never to RoleSprint
About this role
ABOUT THE ROLE
This is a full-stack software engineering role on a small, flat team building an AI agent platform for the hospitality industry. You will own meaningful pieces of a system that handles guest communication and operations workflows at scale, with real autonomy over design and architecture decisions.
WHAT YOU'LL DO
- Design and build response generation pipelines, including routers, orchestrators, and synthesizers that classify intent, assemble context, select tools, and decide when to send or escalate.
- Develop knowledge retrieval systems that ground agent responses in accurate, current customer data despite messy real-world inputs.
- Build tool orchestration layers that execute multi-step workflows reliably, including graceful handling of third-party API failures mid-conversation.
- Create evaluation frameworks that measure quality against real conversations and catch regressions before they reach customers.
- Implement observability and tracing that makes agent reasoning legible to non-technical support teams.
- Design controls and interfaces that let support leads adjust agent behavior without writing code.
- Extend the platform to voice conversations with real-time transcription and tool-use capabilities.
- Optimize for speed and cost through model routing, caching, and prompt refinement.
- Own infrastructure, data pipelines, integrations, and API work that underpin the platform.
WHAT WE'RE LOOKING FOR
- 5+ years of professional software engineering experience, with at least 3 years shipping production systems that real users depend on.
- Hands-on experience designing and debugging AI/ML systems in production, including retrieval pipelines, prompt engineering, or model orchestration.
- Experience building and evaluating retrieval systems such as knowledge bases, ranking, context validation, or semantic search.
- Experience designing multi-step workflows, tool orchestration, or function-calling systems.
- Experience building observability, tracing, or debugging tooling for complex pipelines.
- Strong evaluation discipline, measuring impact across real conversations before shipping changes.
- Proficiency in at least one backend language such as Python, Go, Rust, or Java.
- Comfort working across the full stack and picking up whatever the problem requires.
- Demonstrated direct ownership of production product systems, ideally in a startup environment.
- Experience integrating with third-party APIs and handling failure modes in production.
- Pragmatism about AI models, knowing when to reach for frontier models, fine-tuned variants, or simpler solutions.
- Prior experience with voice systems, real-time audio, or low-latency applications is a plus.
- Background in hospitality, travel, property management, or guest operations is a plus.
COMPENSATION & BENEFITS
- Base salary: $130,000 to $220,000 per year
- Equity: 0.20% to 1.20%
- Comprehensive health insurance and 401(k) match
- Visa sponsorship is not available; candidates must be authorized to work in the US
LOCATION
On-site in San Francisco, CA. Relocation is welcome for the right candidate.
Work location
- San Francisco, CA, US
Related jobs
Ready to make a decision?
This role is either worth your time or it isn’t.
Analyze the posting against your experience, see the gaps clearly, and build the right materials only if the opportunity makes sense.
Nothing is submitted automatically. You choose what happens next.
About this listing
Published on Ashby under the board identifier Clera, which is the name the employer’s own job board carries. RoleSprint has not verified the company’s registered or trading name, so it is shown exactly as published rather than tidied up.
RoleSprint is not the employer and not a recruiter. Applications are made on the employer’s own site and never reach us; what RoleSprint does is help you decide whether a role is worth your time and prepare for it if it is.
Published 27 September 2026, last checked 2 days ago. A posting stops being advertised here 90 days after the employer published it, and one the employer takes down is marked closed rather than quietly removed.