The Team
You’ll join our 8-person, cross-functional GenAI Platform squad. We build and operate a Python API that lets developers define, deploy, and manage autonomous multi-agent workflows—leveraging LLMs, vector-search/RAG, external APIs, memory, and custom logic. Our platform handles agent life-cycle, context routing, error recovery, telemetry, and cost controls, making it simple to assemble complex GenAI-driven features.
The Opportunity
As our next Software Engineer, you will be pivotal in evolving our platform from its Beta launch into an enterprise-ready agent ecosystem. You’ll own fast-follow capabilities, broaden our LLM provider integrations, enhance observability, and harden multi-agent coordination. Your work will accelerate partner adoption and lay the groundwork for compliance and at-scale performance.
Your Role Includes
- Backend API Development & Migration - Design, implement, and maintain Python APIs to achieve sub-100 ms SLAs on cached calls, containerize for GCP, and ensure zero-downtime rollouts.
- Agentic “Tool” Integration - Extend our orchestration engine to treat RAG (vector-search + prompt templates) as a first-class tool; build and maintain SDK adapters for leading LLM providers and vector stores.
- Production Hardening & Best Practices - Enforce rigorous type-hinting, linting, CI/CD, smoke tests, and full coverage; automate canary deployments and performance tuning in a microservices environment.
- Observability, Security & Cost Controls - Instrument detailed telemetry (cache hits/misses, API-call metrics, LLM costs); build dashboards for internal teams; implement RBAC, audit logging, rate-limiting, and per-tenant isolation.
- Customer Enablement - Partner with technical customer teams and Solutions Engineers to create documentation, demos, and sample apps that accelerate onboarding and drive adoption.
Day-to-Day
- Participate in agile rituals (planning, stand-ups, reviews, retrospectives)
- Pair- or mob-program on major features (e.g., multi-agent recovery logic, new LLM adapters)
- Write and review high-quality Python code and RFC-backed pull requests
- Keep runbooks and API specs “always green” in Confluence
- Troubleshoot production issues via logs and roll out hot-fixes as needed
Key Projects & Initiatives
- Beta Fast-Follow: semantic & response caching, multi-vendor routing logic, enterprise SLA codification
- Orchestration Enhancements: dynamic tool-chaining, context routing improvements, dead-letter handling
- Telemetry Dashboards: cost-savings insights, request-prioritization controls
- Python SDK & Sample Apps: robust client library and reference multi-agent workflows
You Might Be a Fit If You Have
- Python & API Design: 3+ years building versioned REST APIs in FastAPI or Django REST Framework, with strong type safety and unit tests
- Generative-AI Expertise: hands-on experience integrating LLM providers and designing multi-agent orchestration logic in Python
- Microservices Production Skills: familiarity with Docker/GCP, performance tuning, canary rollouts, and low-latency caching
- Observability & Security Acumen: experience instrumenting telemetry, implementing RBAC/audit logging, rate-limiting, and multi-tenant isolation
- Collaborative Mindset: proven ability to thrive in pair/mob programming, contribute to RFCs, and uphold collective code ownership
- Bonus Skills: Terraform/IaC, advanced GCP services (Cloud Run, Pub/Sub), React/TypeScript, experience with Algolia’s search ecosystem
Our Values in Action
- GRIT: Navigate ambiguity and technical challenges with perseverance
- TRUST: Collaborate openly, take ownership, and build confidence across teams
- CANDOR: Give and receive constructive feedback to drive improvement
- CARE: Show genuine empathy for teammates and customers
- HUMILITY: Remain curious, acknowledge mistakes, and learn from others
Flexible workplace strategy: Algolia’s flexible workplace model is designed to empower all Algolians to fulfill our mission to power search and discovery with ease. We place an emphasis on an individual’s impact, contribution, and output, over their physical location. Algolia is a high-trust environment and many of our team members have the autonomy to choose where they want to work and when.
While we have a global presence with physical offices in Paris, NYC, London, Sydney and Bucharest, we also offer many of our team members the option to work remotely either as fully remote or hybrid-remote employees. Please note that positions listed as "Remote" are only available for remote work within the specified country. Positions listed within a specific city are only available in that location - depending on the nature of the role it may be available with either a hybrid-remote or in-office schedule.