Senior Software Engineer - Generative Chat Applications

Fetch

75d

About The Position

Fetch is building the future of personalized consumer experiences. We’re looking for a Senior Software Engineer, Generative Chat Applications to drive the technical strategy and implementation of LLM-powered conversational systems across Fetch. You’ll play a central role in advancing our flagship generative AI product, FAST, while collaborating with engineers working on chat and interactive agent experiences throughout the company. This is a high-impact role focused on building production-grade, low-latency chat systems that deliver fast, engaging, and reliable experiences at scale. You’ll partner closely with product, data, and design teams to bring innovative conversational features to life, transforming prototypes into systems used by millions of Fetch users.

Requirements

• 5+ years of professional software engineering experience, including 1 year focused on generative chat applications.
• Proven experience building or scaling production systems leveraging LLMs (retrieval-augmented generation, fine-tuning, or agent frameworks).
• Strong software engineering background (distributed systems, APIs, data pipelines, or backend services).
• Experience building LLM-based chat interfaces and implementing evaluation systems for conversational quality.
• Experience optimizing conversational applications for low latency and high reliability.
• Demonstrated ability to mentor engineers, provide clear design guidance, and break complex problems into actionable tasks.
• Strong communication and collaboration skills, with experience partnering cross-functionally to deliver impactful features.
• Comfortable navigating high-ambiguity environments, driving clarity and measurable outcomes in fast-moving settings.
• Familiarity with LLM agent frameworks (LangGraph, OpenAI Agents SDK, Semantic Kernel, etc.) and orchestration patterns.

Nice To Haves

• Experience with classical NLP techniques such as sentiment analysis, translation, or token classification.
• Experience fine-tuning LLMs for domain-specific applications.
• Experience designing and maintaining large-scale Python codebases and contributing to shared technical standards.
• Knowledge of retrieval systems, embeddings, and evaluation frameworks for conversational AI.
• Exposure to multi-modal LLM applications (text + images, structured data, etc.).
• Proven ability to influence peers through technical leadership, raise engineering quality, and foster a culture of learning and mentorship.
• Prior experience bridging application engineering with AI/ML model integration and serving.

Responsibilities

• Drive the technical strategy, architecture, and implementation of generative chat applications across Fetch.
• Design and develop new features for FAST, Fetch’s flagship generative AI product.
• Build evaluation frameworks that measure and improve conversational quality, latency, and overall user experience.
• Scale and extend LLM-driven systems for FAST, FetchGPT, and Analyst Agents to handle consumer-scale usage.
• Evolve prototypes into production-grade systems with robust observability, evaluation, and safety practices.
• Mentor engineers working on chat experiences, raising the bar for design, integration, and responsible AI usage.
• Collaborate with cross-functional partners to deliver chat-first, user-adaptive experiences.
• Use AI tools to accelerate development, including validating product ideas in LLM sandboxes, leveraging AI for code generation, and exploring LLMs to enhance analyst workflows.

Benefits

• Equity: We offer employees equity in Fetch, so that everyone can benefit from Fetch’s growth.
• 401k Match: Dollar-for-dollar match up to 4%.
• Benefits for humans and pets: We offer comprehensive medical, dental and vision plans for everyone including your pets.
• Continuing Education: Fetch provides ten thousand per year in education reimbursement.
• Employee Resource Groups: Take part in employee-led groups that are centered around fostering a diverse and inclusive workplace through events, dialogue and advocacy.
• Paid Time Off: On top of our flexible PTO, Fetch observes 9 paid holidays, including Juneteenth and Indigenous People’s Day, as well as our year-end week-long break.
• Robust Leave Policies: 20 weeks of paid parental leave for primary caregivers, 14 weeks for secondary caregivers, and a flexible return to work schedule.
• Calvin Care Cash: Employees who are welcoming new family members will also receive a one time $2,000 incentive to assist employees with covering the cost of childcare, clothing, diapers and much more.
• Flexible Work Environment: Collaborate with your team in one of our stunning offices in Madison, Birmingham, or Chicago. Or you can work fully remotely from anywhere in the US.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Number of Employees: 501-1,000 employees