What are the responsibilities and job description for the Senior Software Engineer, Agents position at fermat?
FERMÀT is the AI native commerce platform that optimizes shopping experiences, leading to best-in-class shopper engagement and conversion. We help brands transform clicks into conversions with dynamic, personalized shopping experiences—built and optimized in minutes.
Backed by VMG, Bain Capital Ventures, Greylock, QED, and named The Information’s #1 commerce startup, we’re a 70 person team based in SF, Austin, NYC, and Bangalore. As a fast-growing Series B company, we’re building the infrastructure for the future of online retail—and we’re just getting started.
About the Role:
We’re searching for a product‑minded Software Engineer to help build out Pierre, FERMÀT’s AI Agent, into a production‑grade intelligence engine that powers personalization, automation, and operational insights across our commerce platform. You will design and build LLM‑powered features end‑to‑end: orchestration (tools/agents/function‑calling), retrieval, evaluations and productionization (APIs, observability, cost/latency). If you love turning ambiguous problems into shipped experiences—and you have experience taking AI products to market in the last 12 to 18 months, this role is for you.
What You'll Work On:
- Take AI products to market: prototype quickly, instrument, A/B test, and iterate based on quality, conversion impact, latency, and cost.
- Own LLM orchestration: multi-agent systems, tool use, function‑calling, structured outputs, routing, context windows, retrieval and evals.
- Build evaluation & observability: golden datasets, automated evals, prompt/version management and monitoring.
- Productionize reliably: scalable APIs/services, workers/queues, caching and provider failover. Optimize performance while keeping costs reasonable.
- Data foundations: integrate first‑party events and catalog data; respect data contracts.
- Vendor strategy: evaluate and integrate multiple model providers (e.g., OpenAI, Anthropic, Google) while tracking quality, cost, and reliability.
- Raise the bar: document best practices, lead design reviews, and mentor engineers on AI patterns.
What We're Looking For:
- 4 years of professional software engineering experience.
- 12–18 months building and shipping LLM‑powered products (from prototype to GA) with meaningful customer adoption. Please include links, demos, or a brief write‑up if possible.
- Strong Python and TypeScript experience. Solid systems design and API fundamentals.
- Hands‑on with LLM APIs, embeddings, vector databases, retrieval patterns and agent/tool design.
- Pragmatic prompt engineering and prompt/version control
- Production chops: cloud (GCP), containers, CI/CD, monitoring/alerting; comfort owning services in prod.
- Product sense, clear communication, and a bias to ship.
Nice to Have:
- E‑commerce, recommendations, ranking or ads experience.
- Experience with streaming responses, Streamable HTTP/SSE/WebSocket patterns for real-time AI interactions.
- Real‑time personalization and event pipelines (e.g., Kafka, pub/sub).
- Front‑end (React) skills for rapid prototyping of AI UX.
- Experimentation/analytics tools (e.g., PostHog or similar).
Benefits
- Competitive salary equity package
- Comprehensive health, dental, and vision insurance for you and all your dependents.
- Retirement benefits:
- US: 401(k) plan with 4% matching
- India: Provident Fund with 12% matching
- 4 months of paid parental leave
- Unlimited PTO policy (with minimum 5 days PTO / quarter!)