Clerk Chat, Inc.
Staff Software Engineer San Francisco
Clerk Chat, Inc., San Francisco, California, United States, 94199
Clerk Chat's mission is to make every business conversational. We are achieving this by building the leading messaging application, integrating AI where it matters, and crafting our own telecom infrastructure. It's big and bold and needs spirited adventurers to join our growing team.
We've built Clerk Chat organically into a profitable business over the last 2 years. We're a team that believes in achieving your highest potential but not at the expense of work‑life balance. That's why we have flexible vacation time, healthy quarterly bonuses, and creative freedom at the forefront. We're Silicon Valley‑based entrepreneurs who have sold companies, gone through HF0, and built teams at Lucasfilms, Samsung, Netflix, DocuSign, and Series B+ Startups.
What does a work environment look like at Clerk Chat? Clerk Chat is an in‑office team based just three blocks south of the Embarcadero BART station, making it easy to commute and stay connected. We love being in the office five days a week because it fosters real‑time collaboration, builds stronger relationships, and helps us move faster. This is an exciting time to join Clerk Chat. We're small enough that every individual has a big impact, but we're growing fast enough that there's tremendous room for career advancement.
Who You Are As a Staff Software Engineer focused on Backend & AI, you are a technical leader who thrives at the intersection of systems engineering and applied AI. You're obsessed with building reliable, low‑latency infrastructure and equally passionate about crafting prompts and orchestration layers that make AI feel magical. You understand that great AI products aren't just about the models—they're about the systems that surround them. You take ownership of complex problems, influence technical direction across teams, and elevate those around you.
What You Will Do
Design and build backend systems
that power real‑time voice AI at scale, with a relentless focus on latency, reliability, and observability
Develop and refine AI prompting strategies
for conversational voice agents, optimizing for natural dialogue, accuracy, and edge‑case handling
Own the AI orchestration layer
— from prompt engineering to context management, tool calling, and response streaming
Drive architectural decisions
that shape our voice AI pipeline, including integration with STT, TTS, and LLM providers
Build evaluation frameworks
to measure and iterate on AI performance, including automated testing for prompt quality and regression detection
Collaborate closely with product and customers
to translate real‑world use cases into robust AI behaviors
Mentor engineers
and raise the technical bar across the organization
Contribute to technical strategy
as a key voice in how we build and scale our platform
What You Will Need
10+ years of software engineering experience , with significant time spent in backend or infrastructure roles
Deep expertise in Python or Go
(or similar languages) for building production systems
Hands‑on experience with LLMs
— prompt engineering, fine‑tuning, RAG architectures, or building AI‑powered features
Strong understanding of distributed systems , including event‑driven architectures, async processing, and real‑time data pipelines
Experience with low‑latency systems
where milliseconds matter
Track record of technical leadership
— influencing architecture, mentoring engineers, and driving cross‑functional initiatives
Excellent communication skills
— you can explain complex technical concepts clearly to both engineers and non‑technical stakeholders
A bias toward shipping
— you balance technical excellence with pragmatism
Nice to Have
Experience with
voice AI, telephony, or real‑time communication systems
(WebRTC, SIP, SBCs)
Familiarity with
speech‑to‑text, text‑to‑speech, or VAD
technologies
Background in
prompt optimization
at scale—A/B testing prompts, building prompt management systems
Experience with
telecom, contact center, or conversational AI
products
Exposure to
early‑stage startups or high‑growth companies , with a passion for driving results in fast‑moving environments
What We Offer
Competitive compensation and equity packages
Health, dental, and vision insurance
Flexible vacation time (Unlimited PTO)
401k with 4% match
Quarterly bonuses
The opportunity to shape the future of conversational AI at a company where your work directly impacts the product
As set forth in Clerk Chat’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law.
#J-18808-Ljbffr
We've built Clerk Chat organically into a profitable business over the last 2 years. We're a team that believes in achieving your highest potential but not at the expense of work‑life balance. That's why we have flexible vacation time, healthy quarterly bonuses, and creative freedom at the forefront. We're Silicon Valley‑based entrepreneurs who have sold companies, gone through HF0, and built teams at Lucasfilms, Samsung, Netflix, DocuSign, and Series B+ Startups.
What does a work environment look like at Clerk Chat? Clerk Chat is an in‑office team based just three blocks south of the Embarcadero BART station, making it easy to commute and stay connected. We love being in the office five days a week because it fosters real‑time collaboration, builds stronger relationships, and helps us move faster. This is an exciting time to join Clerk Chat. We're small enough that every individual has a big impact, but we're growing fast enough that there's tremendous room for career advancement.
Who You Are As a Staff Software Engineer focused on Backend & AI, you are a technical leader who thrives at the intersection of systems engineering and applied AI. You're obsessed with building reliable, low‑latency infrastructure and equally passionate about crafting prompts and orchestration layers that make AI feel magical. You understand that great AI products aren't just about the models—they're about the systems that surround them. You take ownership of complex problems, influence technical direction across teams, and elevate those around you.
What You Will Do
Design and build backend systems
that power real‑time voice AI at scale, with a relentless focus on latency, reliability, and observability
Develop and refine AI prompting strategies
for conversational voice agents, optimizing for natural dialogue, accuracy, and edge‑case handling
Own the AI orchestration layer
— from prompt engineering to context management, tool calling, and response streaming
Drive architectural decisions
that shape our voice AI pipeline, including integration with STT, TTS, and LLM providers
Build evaluation frameworks
to measure and iterate on AI performance, including automated testing for prompt quality and regression detection
Collaborate closely with product and customers
to translate real‑world use cases into robust AI behaviors
Mentor engineers
and raise the technical bar across the organization
Contribute to technical strategy
as a key voice in how we build and scale our platform
What You Will Need
10+ years of software engineering experience , with significant time spent in backend or infrastructure roles
Deep expertise in Python or Go
(or similar languages) for building production systems
Hands‑on experience with LLMs
— prompt engineering, fine‑tuning, RAG architectures, or building AI‑powered features
Strong understanding of distributed systems , including event‑driven architectures, async processing, and real‑time data pipelines
Experience with low‑latency systems
where milliseconds matter
Track record of technical leadership
— influencing architecture, mentoring engineers, and driving cross‑functional initiatives
Excellent communication skills
— you can explain complex technical concepts clearly to both engineers and non‑technical stakeholders
A bias toward shipping
— you balance technical excellence with pragmatism
Nice to Have
Experience with
voice AI, telephony, or real‑time communication systems
(WebRTC, SIP, SBCs)
Familiarity with
speech‑to‑text, text‑to‑speech, or VAD
technologies
Background in
prompt optimization
at scale—A/B testing prompts, building prompt management systems
Experience with
telecom, contact center, or conversational AI
products
Exposure to
early‑stage startups or high‑growth companies , with a passion for driving results in fast‑moving environments
What We Offer
Competitive compensation and equity packages
Health, dental, and vision insurance
Flexible vacation time (Unlimited PTO)
401k with 4% match
Quarterly bonuses
The opportunity to shape the future of conversational AI at a company where your work directly impacts the product
As set forth in Clerk Chat’s Equal Employment Opportunity policy, we do not discriminate on the basis of any protected group status under any applicable law.
#J-18808-Ljbffr