Senior Software Engineer

Senior Software Engineer

Employment Type: Full-time
FLSA Status: Exempt
Location: San Francisco, CA (In Office)

Compensation: 150K-170K salary

About Abby Connect

Abby Connect is a fast-growing customer experience company helping small businesses deliver personal, professional, and scalable communication. Our live receptionist services have powered thousands of client interactions every day for over a decade, and we’re now expanding our technology portfolio with AI-driven products that combine human empathy with intelligent automation.

The AI Receptionist Platform is Abby Connect’s latest innovation — an intelligent voice system that manages scheduling, intake, and communication in natural conversation. It’s a critical part of our long-term strategy to redefine how businesses handle customer calls.

The Role

We’re hiring a Senior Software Engineer to help build, improve, and scale Abby’s core software platform, including both our AI-powered products and our internal operational systems.

This is a hands-on, execution-focused role working closely with our Principal Engineer. You will:

• Build and ship features across multiple systems (AI platform, internal tools, customer-facing apps)
• Own meaningful components end-to-end (backend, APIs, and UI)
• Improve system reliability, performance, and developer velocity
• Contribute to the evolution of Abby’s technology as we transition fully to an in-house engineering team

What You’ll Do

Backend & Platform Engineering (Primary Focus)

• Build and maintain production-grade APIs and services using Python and/or TypeScript where needed
• Work across Abby’s core platform, including internal tools, integrations, and customer-facing systems
• Design and implement scalable services, data flows, and system integrations
• Work with queues, async processing, and external APIs
• Debug production issues and improve system performance and reliability

AI / LLM Product Development

• Contribute to AI-powered features within the AI Receptionist and other internal tools
• Integrate LLM APIs (OpenAI, Anthropic, etc.) into real product workflows
• Assist in improving prompt engineering, evaluation, and output reliability
• Support development of RAG pipelines and retrieval-based systems and tool-calling flows
• Help optimize LLM cost, latency and accuracy in production

Full-Stack Development

• Build and enhance internal tools and customer-facing features using React
• Deliver complete features across frontend and backend
• Collaborate on UX decisions to ensure clean, intuitive, and performant interfaces

Engineering Quality & Execution

• Write clean, maintainable, and well-tested code
• Participate in code reviews and uphold engineering standards
• Improve CI/CD, testing, and deployment practices
• Ship quickly while maintaining a high-quality bar

Platform Ownership & Evolution

• Help stabilize and improve systems previously built by external vendors
• Contribute to refactoring, simplification, and standardization of the codebase
• Support the transition to a fully internal engineering team

Collaboration

• Work closely with the Principal Engineer, CEO, and Product team
• Partner with operations and support teams to understand real-world workflows
• Contribute to a strong engineering culture aligned with Abby’s values

Who We’re Looking For

• 3–6+ years of hands-on software engineering experience
• Strong proficiency in Python (primary background language) and TypeScript
• Experience building production backend systems and APIs
• Experience working across multiple systems (not just a single isolated service)
• Strong debugging and problem-solving skills
• Proven ability to ship features end-to-end in production
• Hands-on experience integrating LLM APIs, building RAG pipelines, or working with embeddings/vector search

Bonus but valuable:

• Voice AI experienced (STT/TTS, Eleven Labs, Whisper, Twilio, WebRTC, SIP)
• Real-time or event-driven systems
• Experience at an early-stage startup or small engineering team

Why Join Abby Connect

• Real Ownership: Work across multiple critical systems that power the business
• Impact: Your work directly affects both customers and internal operations
• Growth: Learn from a strong Principal Engineer and grow into more ownership
• Stability + Innovation: Profitable company expanding into AI-driven products
• Mission: We believe the future of customer service combines human understanding with AI precision

Pay: $150,000.00 - $170,000.00 per year

Benefits:

• 401(k)
• 401(k) matching
• Bereavement leave
• Dental insurance
• Employee assistance program
• Health insurance
• Life insurance
• Paid holidays
• Paid jury duty
• Paid time off
• Parental leave
• Referral program
• Sabbatical
• Vision insurance

Application Question(s):

• Are you located in San Francisco or within commutable distance? This is an in-person role in our San Francisco office.
• Can you describe a recent project where you personally built and shipped an AI/LLM feature (e.g., RAG pipeline, agent workflow, LLM-integrated API)?
• Are you comfortable writing production-level code daily in either TypeScript or Python?
• Have you directly implemented vector search or retrieval-augmented generation (RAG) using tools like Pinecone, Weaviate, FAISS, Qdrant, or a similar vector DB?
• Do you have experience working in a fast-paced startup or small engineering team where you owned features end-to-end (architecture → code → testing → deployment)?

Work Location: In person